© 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. 93237
    Prev
    Next
    INDEX
    Explanations

    protected code keywords

    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
     Yiddish
    -0.71
    itzar
    -0.69
     closure
    -0.68
    asons
    -0.66
    zionato
    -0.66
    finally
    -0.66
    ごとの
    -0.66
     %>
    -0.65
    logout
    -0.65
     Andean
    -0.65
    POSITIVE LOGITS
     umano
    0.77
    Bruh
    0.77
    国の
    0.75
     cal
    0.73
     проживания
    0.73
    Peaceful
    0.70
     inesperado
    0.70
     Shri
    0.69
     íntimo
    0.69
     تج
    0.68
    Activations Density 0.070%

    No Known Activations