© 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. 72164
    Prev
    Next
    INDEX
    Explanations

    code, programming, web development

    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
     more
    -2.02
    <bos>
    -1.98
     It
    -1.90
     extraordinarily
    -1.85
     other
    -1.73
     nearly
    -1.69
     less
    -1.63
     seeks
    -1.63
     Just
    -1.62
     before
    -1.60
    POSITIVE LOGITS
     unſ
    2.25
     a
    2.20
    栳
    1.99
     saati
    1.89
    
    1.87
    跸
    1.87
     spesifik
    1.86
    躂
    1.82
    waitKey
    1.80
     köy
    1.78
    Activations Density 0.002%

    No Known Activations