© 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. 73555
    Prev
    Next
    INDEX
    Explanations

    code and comments punctuation

    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
    Not in Any Lists

    No Comments

    Negative Logits
     fuma
    -1.05
     rocha
    -1.03
     responsab
    -1.02
    糨
    -1.02
     hilfre
    -1.02
     faca
    -0.99
     sirop
    -0.99
     }</
    -0.98
     ochi
    -0.98
     munc
    -0.97
    POSITIVE LOGITS
     or
    1.10
    ↵
    0.97
    ,
    0.93
     -
    0.90
     ü
    0.89
     Kalifor
    0.89
    鋅
    0.88
    べて
    0.87
    You
    0.87
    larda
    0.86
    Activations Density 0.015%

    No Known Activations