© 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. 22-GEMMASCOPE-RES-131K
    7. 25201
    Prev
    Next
    INDEX
    Explanations

    drama television series

    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_22/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
    k
    -1.05
    U
    -1.04
    atype
    -0.99
    .
    -0.97
    g
    -0.96
    Q
    -0.95
    P
    -0.94
    $
    -0.94
     MaterialApp
    -0.93
    лкой
    -0.92
    POSITIVE LOGITS
    setLong
    1.33
    tvguide
    1.30
     Empieza
    1.25
     rövid
    1.19
    íguez
    1.17
    uniqlo
    1.13
     сериала
    1.11
     personajes
    1.11
    ämme
    1.07
     Briefly
    1.05
    Activations Density 0.014%

    No Known Activations