© 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. 22484
    Prev
    Next
    INDEX
    Explanations

    keys in data structures

    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
    ,
    -2.05
     eivät
    -1.66
     différents
    -1.61
     permettent
    -1.59
     empêcher
    -1.59
     liés
    -1.55
     spannende
    -1.55
     pourraient
    -1.55
     attentes
    -1.55
     неё
    -1.54
    POSITIVE LOGITS
     will
    1.82
     was
    1.70
     fria
    1.66
     through
    1.59
     using
    1.54
     chão
    1.52
     an
    1.48
     pecuni
    1.47
     and
    1.46
     gratific
    1.45
    Activations Density 0.018%

    No Known Activations