© 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. 132673
    Prev
    Next
    INDEX
    Explanations

    normally would

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

    descriptions of actions or components

    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
     progenitors
    0.53
     unidos
    0.52
     inhomogeneities
    0.50
     unn
    0.48
     elution
    0.48
     Locations
    0.48
     /(
    0.48
     thresholds
    0.48
     elevations
    0.47
     Ε
    0.47
    POSITIVE LOGITS
    DetailPage
    0.50
     상세보기
    0.48
    Interactive
    0.45
    Etiam
    0.45
     paragraphe
    0.45
    Osaka
    0.44
    Deja
    0.44
     सांस
    0.44
    ನಗೆ
    0.43
    Antib
    0.43
    Activations Density 0.000%

    No Known Activations