© 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. 65142
    Prev
    Next
    INDEX
    Explanations

    completion of a state or task

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

    completion of tasks

    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
    t
    0.66
    das
    0.50
     discontinuation
    0.49
    ON
    0.47
    d
    0.47
     canlı
    0.47
     tokom
    0.47
     कंटिन्यू
    0.47
     ده
    0.46
     fulfil
    0.46
    POSITIVE LOGITS
     inserting
    0.52
     гуляць
    0.50
    꿩
    0.50
    কুম
    0.49
     cargar
    0.49
    Ссылка
    0.48
    ologischen
    0.48
    வாய
    0.48
    த்திலிருந்து
    0.48
    скохозяй
    0.48
    Activations Density 0.031%

    No Known Activations