© 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. 15374
    Prev
    Next
    INDEX
    Explanations

    getter in 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
     focuses
    -1.66
     to
    -1.56
     a
    -1.55
    柺
    -1.45
     Entwurf
    -1.44
    pantalón
    -1.43
     avowed
    -1.43
     repre
    -1.42
     ardından
    -1.42
     then
    -1.41
    POSITIVE LOGITS
    '
    1.73
    There
    1.70
    there
    1.64
    .
    1.63
    It
    1.62
     relics
    1.52
    ✨
    1.52
    💕
    1.49
     бъдат
    1.49
    they
    1.48
    Activations Density 0.003%

    No Known Activations