© 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. 34-GEMMASCOPE-RES-131K
    7. 47278
    Prev
    Next
    INDEX
    Explanations

    option or number sequences

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Leve
    -0.72
    ticello
    -0.69
    Lifting
    -0.68
    leaner
    -0.68
    ளி
    -0.66
    nexpected
    -0.66
    運
    -0.65
    ikan
    -0.65
    modelName
    -0.65
    Protective
    -0.64
    POSITIVE LOGITS
    rolid
    0.76
     Ashley
    0.69
    Page
    0.68
    Ϊ
    0.67
     bire
    0.67
    TryGetValue
    0.66
    Assign
    0.66
     Hentet
    0.66
    getType
    0.66
    Queen
    0.66
    Activations Density 0.060%

    No Known Activations