© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79113
    Prev
    Next
    INDEX
    Explanations

    vector bundle

    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
    Not in Any Lists

    No Comments

    Negative Logits
    keySet
    -0.73
    ="/
    -0.72
     Ring
    -0.68
    kör
    -0.68
     острова
    -0.67
     chin
    -0.66
     SCC
    -0.66
    ushy
    -0.66
     Strauss
    -0.65
     Kör
    -0.65
    POSITIVE LOGITS
     bundle
    1.44
     bundles
    1.35
    Bundle
    1.27
     Bundle
    1.25
    bundle
    1.20
    bundles
    1.19
    Bundles
    1.02
     Bund
    1.02
     bundled
    0.94
     rank
    0.93
    Activations Density 0.038%

    No Known Activations