© 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. 34-GEMMASCOPE-RES-131K
    7. 58593
    Prev
    Next
    INDEX
    Explanations

    code, file paths, programming language keywords

    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_34/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
    STAND
    -0.68
    ofire
    -0.65
     acrylique
    -0.65
     cí
    -0.64
    wiel
    -0.63
     Workshop
    -0.63
    SUFFIX
    -0.63
     замок
    -0.63
     Victims
    -0.63
     Stand
    -0.63
    POSITIVE LOGITS
     grinned
    0.73
     FAX
    0.71
    screen
    0.67
    tration
    0.67
    летия
    0.66
     FORE
    0.66
     provocar
    0.65
    xmlns
    0.65
    tilization
    0.63
     בנו
    0.63
    Activations Density 0.068%

    No Known Activations