© 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. 39875
    Prev
    Next
    INDEX
    Explanations

    function definitions

    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
    鐽
    -1.82
     daug
    -1.73
    viève
    -1.70
     otak
    -1.66
    vieve
    -1.64
    anians
    -1.63
    氿
    -1.61
     matériel
    -1.58
     PERSONNEL
    -1.56
     Irán
    -1.55
    POSITIVE LOGITS
     it
    2.77
     or
    2.14
     of
    2.14
     not
    2.02
     on
    1.98
     other
    1.85
    as
    1.80
    er
    1.73
     as
    1.72
     In
    1.63
    Activations Density 0.013%

    No Known Activations