© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14521
    Prev
    Next
    INDEX
    Explanations

    social classifications

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron selectively activates on formal legal or administrative terminology and named entities (e.g. formal action verbs like “deems,” “waive,” document-style terms like “Retrieved,” and place names such as “Houston, TX”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    legal or technical text with formal language and terms like "necessary," "accepted," "Retrieved," or modal verbs indicating obligation or possibility.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    formal, boilerplate-style text found in legal terms, academic citations, and structured location metadata.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    m
    1.27
    t
    1.19
    e
    1.18
    '
    1.14
    p
    1.01
    d
    0.96
    s
    0.91
    r
    0.89
    g
    0.88
    c
    0.84
    POSITIVE LOGITS
     asymptotically
    0.90
     equivari
    0.88
     congruence
    0.87
     uphold
    0.86
     eukary
    0.85
     invariance
    0.82
     apartheid
    0.82
    сё
    0.82
    стры
    0.82
     Hermitian
    0.82
    Activations Density 0.001%

    No Known Activations