© 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. 150568
    Prev
    Next
    INDEX
    Explanations

    ballroom dancing, collect, send, award, letter

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

    in_channels or out_channels

    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
     :::
    0.49
     αποτε
    0.47
    etag
    0.47
     Eva
    0.46
    刨
    0.46
    raulic
    0.46
     ανε
    0.46
    emulator
    0.45
    ;
    0.45
    ([-
    0.44
    POSITIVE LOGITS
     documentos
    0.52
    ம்
    0.49
    SHIP
    0.48
     comien
    0.47
    Ссылки
    0.46
    DOCUMENT
    0.46
     campo
    0.46
    Document
    0.46
    ОВ
    0.46
    ം
    0.45
    Activations Density 0.001%

    No Known Activations