© 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. 14795
    Prev
    Next
    INDEX
    Explanations

    html markup and code

    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
     will
    -1.84
     Its
    -1.83
     
    -1.70
     a
    -1.70
     is
    -1.70
    它的
    -1.56
    -
    -1.55
    {
    -1.54
    只好
    -1.53
    </b>
    -1.50
    POSITIVE LOGITS
     ",";
    1.75
    providedIn
    1.73
     élégant
    1.67
     /\.
    1.66
     ""));
    1.62
     IBOutlet
    1.59
     which
    1.54
     élégante
    1.53
    佧
    1.52
    iência
    1.52
    Activations Density 0.001%

    No Known Activations