© 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. 93198
    Prev
    Next
    INDEX
    Explanations

    python 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
     pymongo
    -0.80
     museum
    -0.79
     respond
    -0.77
    एको
    -0.76
     Pamela
    -0.76
    Buster
    -0.76
     Artikel
    -0.75
     déclare
    -0.75
     москов
    -0.73
    有所
    -0.73
    POSITIVE LOGITS
     glob
    1.52
     shutil
    1.37
    shutil
    1.22
    glob
    1.16
     time
    1.10
    ButterKnife
    1.02
    path
    0.93
     path
    0.93
    datetime
    0.92
    stat
    0.92
    Activations Density 0.022%

    No Known Activations