© 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. 30932
    Prev
    Next
    INDEX
    Explanations

    APIs, services, and location data

    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
    存款
    -0.77
    oldown
    -0.71
     leid
    -0.69
    segmented
    -0.69
    testens
    -0.68
    cellaneous
    -0.68
    polated
    -0.66
    מוש
    -0.66
    ٹر
    -0.66
     идут
    -0.65
    POSITIVE LOGITS
     Spotify
    1.78
     Yelp
    1.64
     fours
    1.64
    oursquare
    1.42
    Spotify
    1.27
    yel
    1.25
     spotify
    1.23
     TripAdvisor
    1.13
     Trip
    0.99
     Open
    0.97
    Activations Density 0.059%

    No Known Activations