© 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. 32743
    Prev
    Next
    INDEX
    Explanations

    json, ref, and code identifiers

    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
     großer
    -0.88
     lác
    -0.88
    的存在
    -0.83
     fördern
    -0.82
     protože
    -0.80
     its
    -0.79
    arised
    -0.77
     спо
    -0.77
     powierzchni
    -0.77
    ρε
    -0.76
    POSITIVE LOGITS
     Préférences
    0.88
     État
    0.88
     Jumat
    0.88
     ristor
    0.87
    💓
    0.83
     skriva
    0.83
     rossa
    0.82
     Ligue
    0.80
    🛍
    0.80
    лимпий
    0.79
    Activations Density 0.019%

    No Known Activations