© 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. 10-GEMMASCOPE-RES-131K
    7. 8856
    Prev
    Next
    INDEX
    Explanations

    file paths and codes

    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_10/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
     in
    -2.83
     with
    -2.55
     as
    -2.27
     before
    -2.16
     just
    -2.11
     took
    -2.03
     became
    -1.97
     at
    -1.95
     went
    -1.95
     provided
    -1.94
    POSITIVE LOGITS
     récol
    2.02
     fidé
    1.98
    actéristi
    1.96
     améli
    1.94
     dénon
    1.91
    歺
    1.89
    those
    1.88
    踯
    1.82
    Couleur
    1.82
    ほとん
    1.82
    Activations Density 0.092%

    No Known Activations