© 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. 129361
    Prev
    Next
    INDEX
    Explanations

    politician names

    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
    !
    -1.54
    —"
    -1.34
    "
    -1.30
    //
    -1.24
    /
    -1.23
     даже
    -1.15
     "";
    -1.15
    %
    -1.13
     "
    -1.09
     ".
    -1.09
    POSITIVE LOGITS
     who
    1.50
    がありますが
    1.46
    rdom
    1.40
     yake
    1.32
    neous
    1.27
    yship
    1.23
    ieť
    1.23
     himself
    1.23
     whom
    1.20
    itudine
    1.19
    Activations Density 0.014%

    No Known Activations