© 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. 3502
    Prev
    Next
    INDEX
    Explanations

    categories, tags, and keys

    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
    ("\\
    -0.81
    orbit
    -0.77
    erli
    -0.73
    hook
    -0.72
     ресторан
    -0.69
    ("{
    -0.68
    λει
    -0.68
    ウェア
    -0.66
     countryside
    -0.65
     exiled
    -0.62
    POSITIVE LOGITS
    Bibliografia
    0.80
     菜
    0.69
     intestino
    0.69
     cinturón
    0.68
    liffe
    0.66
    lietta
    0.65
     bagels
    0.65
     Wray
    0.65
    ZN
    0.65
     MODEL
    0.65
    Activations Density 0.068%

    No Known Activations