© 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. 83970
    Prev
    Next
    INDEX
    Explanations

    indicates error or fatal conditions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     was
    -1.47
     เรา
    -1.42
     andern
    -1.37
     trám
    -1.34
    我和
    -1.33
     exceptionally
    -1.33
     exceedingly
    -1.32
    ’
    -1.27
    および
    -1.27
     extremely
    -1.24
    POSITIVE LOGITS
    0
    1.94
     even
    1.62
    癡
    1.55
     даже
    1.45
     حتی
    1.43
    even
    1.41
    訫
    1.40
    Ꮠ
    1.39
     if
    1.38
    Even
    1.38
    Activations Density 0.042%

    No Known Activations