© 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. 3163
    Prev
    Next
    INDEX
    Explanations

    javascript module imports

    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
    okohama
    -0.78
     Bower
    -0.75
    rane
    -0.72
    uchu
    -0.68
    ไตล
    -0.68
     Fielding
    -0.68
     pochod
    -0.67
     Beecher
    -0.66
    ColumnHeader
    -0.66
     kole
    -0.66
    POSITIVE LOGITS
    getObject
    0.73
     Salsa
    0.71
     salic
    0.68
     القد
    0.66
     Himal
    0.64
     garage
    0.64
     Startseite
    0.63
     payloads
    0.63
     Saar
    0.62
    ائب
    0.62
    Activations Density 0.050%

    No Known Activations