© 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. 129130
    Prev
    Next
    INDEX
    Explanations

    Content-Type header

    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
    fuji
    -0.96
    靴
    -0.96
     vēl
    -0.95
    movieId
    -0.93
     izvē
    -0.93
     még
    -0.92
    <blockquote>
    -0.92
    裕
    -0.91
     gyven
    -0.91
    демо
    -0.91
    POSITIVE LOGITS
    並且
    1.14
    證明
    0.96
     calorías
    0.93
    Fär
    0.93
    面對
    0.91
    實際
    0.91
    влении
    0.90
     almendras
    0.90
    下意识
    0.89
    ouvrir
    0.89
    Activations Density 0.009%

    No Known Activations