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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15809
    Prev
    Next
    INDEX
    Explanations

    left

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

    The neuron fires strongly on capitalized named‐entity tokens (e.g. place names, brand/trademark marks, translational headers, etc.).

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

    trademark symbols or markers indicating brand names and registered entities.

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

    title-cased or otherwise marked named-entity tokens (proper nouns like places, brands, and trademarked terms) within headline-style text.

    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
     ASF
    0.92
     adipose
    0.91
     resultArray
    0.90
     algebraically
    0.88
     pesso
    0.87
     irrever
    0.86
     kaleidos
    0.86
     parabola
    0.84
     ellipt
    0.83
     auricular
    0.83
    POSITIVE LOGITS
    生效
    0.71
    ങ്കിലും
    0.69
    ચ
    0.68
    defined
    0.66
    Zoo
    0.66
    撐
    0.66
    गा
    0.65
    ço
    0.65
    unches
    0.65
    ছেন
    0.64
    Activations Density 0.001%

    No Known Activations