© 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. 16671
    Prev
    Next
    INDEX
    Explanations

    code, data, and non-English 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
     offre
    -1.12
    ΤΕ
    -1.03
     nhan
    -1.02
    bof
    -0.99
    #"
    -0.99
    ‗
    -0.98
    oof
    -0.97
     casino
    -0.97
     plantillas
    -0.96
     Toast
    -0.95
    POSITIVE LOGITS
    Transcripción
    1.08
    Rüyada
    1.02
     đảm
    1.00
    Более
    0.98
    Один
    0.91
    Дополнитель
    0.90
    REUTERS
    0.89
    Кроме
    0.87
    Важно
    0.87
     unabhäng
    0.85
    Activations Density 0.003%

    No Known Activations