© 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. 57882
    Prev
    Next
    INDEX
    Explanations

    cooking ingredients and recipes

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

    GitHub Copilot and code

    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
    in
    0.48
    ز
    0.48
    ar
    0.47
     FTC
    0.43
    ਬ
    0.43
     stink
    0.43
    hass
    0.42
    ع
    0.42
    out
    0.42
    ढ़ी
    0.41
    POSITIVE LOGITS
     znajdują
    0.56
    玛
    0.49
     comenzó
    0.48
     Mā
    0.48
     spagn
    0.48
    Mode
    0.47
     Số
    0.47
    🤴
    0.46
     Paryayvachi
    0.46
    Thể
    0.46
    Activations Density 0.001%

    No Known Activations