© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113085
    Prev
    Next
    INDEX
    Explanations

    Krist, nth, Bluetooth, Brunswick

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    蘼
    -3.44
    捽
    -3.08
    ᝢ
    -3.00
    푙
    -2.92
    嘬
    -2.83
    你这个
    -2.78
    ꈊ
    -2.75
    俛
    -2.73
    derdag
    -2.69
    ఙ
    -2.61
    POSITIVE LOGITS
    '
    4.75
    {
    3.23
    ;
    3.16
    -
    2.97
    [
    2.83
    ();
    2.77
    ,.
    2.73
    ,,
    2.67
    然后
    2.61
    (),
    2.58
    Activations Density 0.004%

    No Known Activations