© 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. 72086
    Prev
    Next
    INDEX
    Explanations

    admission costs and requirements

    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
    他就
    -2.52
    垍
    -2.33
    」　
    -2.30
    ‐
    -2.30
    中国的
    -2.20
    '
    -2.14
    してみてください
    -2.14
    很多的
    -2.08
     noticed
    -2.06
    as
    -2.02
    POSITIVE LOGITS
    ра
    2.66
    o
    2.63
    
    2.48
    刳
    2.36
     theses
    2.36
    挲
    2.27
    ㉕
    2.25
    
    2.17
    Mientras
    2.16
    OUTUBE
    2.13
    Activations Density 0.004%

    No Known Activations