© 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. 10-GEMMASCOPE-RES-131K
    7. 6904
    Prev
    Next
    INDEX
    Explanations

    Punctuation and proper nouns

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     but
    -2.02
    ........
    -1.80
     Both
    -1.75
     .....
    -1.75
    </b>
    -1.75
     It
    -1.74
    ?"
    -1.72
    .......
    -1.72
     ....
    -1.68
    One
    -1.61
    POSITIVE LOGITS
    癭
    1.64
    푃
    1.59
    
    1.57
     compromis
    1.56
    sont
    1.56
     kebaya
    1.56
    occasion
    1.50
    Vente
    1.50
     tabac
    1.49
     interrom
    1.49
    Activations Density 0.002%

    No Known Activations