© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 94201
    Prev
    Next
    INDEX
    Explanations

    product attributes or types

    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
    Negative Logits
     gezwungen
    -0.98
    excluding
    -0.97
     deserto
    -0.94
    ​—
    -0.93
     didn
    -0.93
     vasto
    -0.88
     freilich
    -0.85
    லி
    -0.84
    didn
    -0.82
     depo
    -0.82
    POSITIVE LOGITS
     with
    1.69
     in
    1.61
     of
    1.35
     bzw
    1.05
     für
    1.04
    contentInset
    1.04
    лід
    0.98
     conva
    0.98
     without
    0.95
     mewujudkan
    0.95
    Activations Density 0.201%

    No Known Activations