© 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. 24-GEMMASCOPE-2-RES-16K
    7. 3203
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on code‐style identifier names (e.g. parameter or variable names in camelCase or all-lowercase) within documentation.

    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
    下图
    0.77
    ấy
    0.66
    disk
    0.64
    呲
    0.64
    solved
    0.63
    훙
    0.63
    dragging
    0.62
    图形
    0.62
    holomorphic
    0.62
    surface
    0.61
    POSITIVE LOGITS
    ();
    0.97
    ;
    0.94
    ؛
    0.84
     ();
    0.80
    );
    0.79
    ;)
    0.78
     Pokud
    0.73
     เขา
    0.72
     ||
    0.71
     Puede
    0.71
    Activations Density 0.000%

    No Known Activations