© 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. 22-GEMMASCOPE-RES-131K
    7. 64630
    Prev
    Next
    INDEX
    Explanations

    function calls and 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_22/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
    toral
    -0.98
    俢
    -0.97
    UALLY
    -0.96
    volent
    -0.93
     områ
    -0.93
    ichni
    -0.91
    weds
    -0.88
    ′,
    -0.88
    nament
    -0.87
    strahlung
    -0.86
    POSITIVE LOGITS
     on
    1.14
     we
    1.07
     used
    0.93
     now
    0.91
     chosen
    0.91
     with
    0.89
     mismo
    0.88
    FormsModule
    0.88
     expansive
    0.86
     curve
    0.85
    Activations Density 0.021%

    No Known Activations