© 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. 22-GEMMASCOPE-RES-131K
    7. 128336
    Prev
    Next
    INDEX
    Explanations

    GönCalEfDirections

    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_22/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
     of
    -1.29
     in
    -1.27
    ,
    -1.13
     also
    -1.09
     new
    -1.09
     with
    -1.07
     more
    -1.05
    ;
    -1.04
     over
    -1.02
     that
    -0.99
    POSITIVE LOGITS
    ׇ
    1.03
     påvir
    1.01
    フォーマ
    1.01
    Directions
    0.99
     calef
    0.97
    Gön
    0.96
     простой
    0.93
    directions
    0.92
     Grail
    0.92
    ORMAL
    0.91
    Activations Density 0.002%

    No Known Activations