© 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. 75151
    Prev
    Next
    INDEX
    Explanations

    salads stuff

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

    explaining or describing 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
    ErrorHandler
    0.51
     Если
    0.49
     выбор
    0.46
     ถ้า
    0.45
     Кла
    0.45
     suficientes
    0.45
    稒
    0.45
     האי
    0.44
    ":[{"
    0.43
     कहर
    0.43
    POSITIVE LOGITS
    ’
    0.48
     incentiv
    0.47
     दिवसीय
    0.46
     cantilever
    0.45
     participó
    0.45
     incentivize
    0.44
     merchandise
    0.44
    ZO
    0.44
     blunt
    0.43
     Publikum
    0.43
    Activations Density 0.001%

    No Known Activations