© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2665
    Prev
    Next
    INDEX
    Explanations

    similar to creators

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

    The neuron lights up on key factual or informational content words (mainly nouns and verb‐objects) in expository or report‐style text.

    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_31_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
    他说
    0.57
     بالم
    0.57
    来进行
    0.57
    த்திலும்
    0.56
    和我
    0.56
     الشركات
    0.54
     لهذه
    0.54
    $(".
    0.54
     للت
    0.54
    ığım
    0.54
    POSITIVE LOGITS
     Jokowi
    0.96
     milik
    0.89
     LeBron
    0.85
     Netanyahu
    0.84
     Buhari
    0.83
     Mugabe
    0.82
     Bolsonaro
    0.81
    习近平
    0.81
     Beyonce
    0.80
     mantan
    0.80
    Activations Density 0.985%

    No Known Activations