© 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. 3678
    Prev
    Next
    INDEX
    Explanations

    brig-sloop

    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
    Иск
    -0.85
    ܨ
    -0.79
    déric
    -0.73
     新聞
    -0.71
    anglès
    -0.71
    鳟
    -0.71
     巨人
    -0.70
    salomon
    -0.70
    fiesta
    -0.70
    個性
    -0.69
    POSITIVE LOGITS
     ship
    1.02
     sails
    0.90
     осна
    0.87
     bire
    0.85
    ship
    0.82
     szk
    0.82
    ետ
    0.81
     galle
    0.80
    flags
    0.80
     гале
    0.79
    Activations Density 0.037%

    No Known Activations