© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 219719
    Prev
    Next
    INDEX
    Explanations

    request or available in Christmas dinner homes

    np_acts-logits-general · gemini-2.5-flash-lite

    pinpoint slow requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AN
    0.48
    MOR
    0.47
     Artist
    0.47
     ასევე
    0.46
    Artist
    0.46
    Also
    0.45
    ICA
    0.45
    <h2>
    0.45
    <h3>
    0.45
    Amsterdam
    0.45
    POSITIVE LOGITS
     တို့
    0.54
     prenez
    0.54
    perror
    0.53
     rétréc
    0.52
     errores
    0.50
    സ്‌
    0.48
     Fehler
    0.48
     fà
    0.47
     évaluation
    0.47
    elapsed
    0.46
    Activations Density 0.001%

    No Known Activations