© 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. 9895
    Prev
    Next
    INDEX
    Explanations

    AI Models

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

    The neuron strongly activates on explicit numeric tokens—especially bibliographic volume/page numbers and other standalone digits.

    oai_token-act-pair · o4-miniTriggered 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
    av
    0.93
    at
    0.89
    v
    0.86
    ad
    0.85
    l
    0.85
    ne
    0.84
    d
    0.84
    kort
    0.79
    ë
    0.77
    b
    0.77
    POSITIVE LOGITS
     hinges
    0.92
     היה
    0.78
    ダム
    0.75
    をはじめ
    0.75
     admixture
    0.73
     deployed
    0.73
     خوان
    0.70
     rips
    0.70
    ০
    0.70
    椿
    0.70
    Activations Density 0.000%

    No Known Activations