© 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. 7123
    Prev
    Next
    INDEX
    Explanations

    ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ,
    1.02
     in
    1.01
     to
    0.90
     an
    0.88
    :
    0.88
     Hogwarts
    0.86
    .
    0.86
     is
    0.82
     at
    0.82
    ;
    0.81
    POSITIVE LOGITS
    también
    0.85
     വിവിധ
    0.74
    ának
    0.73
    rouw
    0.71
     givenChar
    0.71
    髗
    0.70
     特に
    0.69
    ohnt
    0.69
    誢
    0.68
    если
    0.68
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.