© 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. 113472
    Prev
    Next
    INDEX
    Explanations

    listing things with etc

    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
    },
    -2.25
    ;
    -1.98
    </th>
    -1.95
     Cedex
    -1.88
    ==",
    -1.80
    笵
    -1.78
     juft
    -1.78
    荭
    -1.73
     装着
    -1.73
    ၜ
    -1.72
    POSITIVE LOGITS
    The
    2.31
     Vordergrund
    2.17
     leichte
    2.08
    These
    2.03
     leichten
    2.02
    This
    2.00
     összefoglal
    1.97
    There
    1.95
     grossen
    1.91
     Hinblick
    1.91
    Activations Density 0.007%

    No Known Activations