© 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. 6995
    Prev
    Next
    INDEX
    Explanations

    comparisons with than

    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
    骜
    -3.44
     This
    -3.25
     Strukt
    -2.86
    灕
    -2.72
     中式
    -2.70
    雳
    -2.61
     ہے
    -2.55
    鴬
    -2.53
    gitte
    -2.47
     высокая
    -2.47
    POSITIVE LOGITS
    $
    2.81
    ar
    2.77
    </h5>
    2.75
    2
    2.66
     originally
    2.55
    }
    2.55
    ha
    2.52
    in
    2.47
    v
    2.47
    “
    2.41
    Activations Density 0.054%

    No Known Activations