© 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. 99142
    Prev
    Next
    INDEX
    Explanations

    code function names and programming constructs

    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
     interrom
    -1.99
     basili
    -1.96
     gewi
    -1.94
     hemd
    -1.87
     sooo
    -1.85
     flotte
    -1.77
     herbe
    -1.77
    擼
    -1.75
     lesquelles
    -1.69
     boden
    -1.69
    POSITIVE LOGITS
     on
    2.58
     for
    2.30
     even
    2.22
     with
    2.13
     in
    2.09
     some
    2.09
     at
    2.08
     because
    2.08
     after
    2.03
     will
    1.95
    Activations Density 0.003%

    No Known Activations