© 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. 3299
    Prev
    Next
    INDEX
    Explanations

    `Psi` or `alias` or `title`

    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
    Not in Any Lists

    No Comments

    Negative Logits
     giù
    -0.82
    wget
    -0.73
    惊
    -0.72
     Pute
    -0.72
    igata
    -0.71
    HttpHeaders
    -0.71
    onez
    -0.71
     geografia
    -0.69
    getDocument
    -0.68
     fancied
    -0.68
    POSITIVE LOGITS
    Prime
    0.75
     Ways
    0.71
    Issuer
    0.68
     prime
    0.68
    zusetzen
    0.67
     ujarnya
    0.66
    idenza
    0.66
    bbi
    0.64
    Nhap
    0.64
     says
    0.64
    Activations Density 0.083%

    No Known Activations