© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32839
    Prev
    Next
    INDEX
    Explanations

    programming imports or specific words

    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
    Negative Logits
    Vlast
    -0.98
     avez
    -0.90
    Recht
    -0.89
     maneiras
    -0.88
    ênes
    -0.87
    cidae
    -0.86
     kvalit
    -0.85
     PROVISIONS
    -0.85
    sery
    -0.85
    uldades
    -0.85
    POSITIVE LOGITS
    !
    1.10
    र
    0.98
    ,
    0.94
    ६
    0.92
    =
    0.90
     uitgevoerd
    0.89
    .
    0.88
    १
    0.88
     then
    0.87
    Sequential
    0.82
    Activations Density 0.001%

    No Known Activations