© 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. 34-GEMMASCOPE-RES-131K
    7. 94245
    Prev
    Next
    INDEX
    Explanations

    parenthetical expressions

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     arşivlendi
    -3.83
     (!__
    -3.48
    (!__
    -3.14
    (!_
    -2.28
     vijf
    -1.94
     geweldige
    -1.84
     /*#__
    -1.84
     установить
    -1.83
     jezt
    -1.81
     realizzare
    -1.80
    POSITIVE LOGITS
     (
    9.25
    (
    2.45
    （
    2.16
     ((
    2.11
    ？（
    1.95
     ("
    1.84
     ('
    1.75
     Although
    1.74
     paredes
    1.74
     цвят
    1.71
    Activations Density 2.235%

    No Known Activations