© 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. 175323
    Prev
    Next
    INDEX
    Explanations

    listing specific items

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

    effort and expertise

    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
    تدائي
    0.51
    স্তক
    0.50
    出
    0.47
     নেতৃত্বের
    0.46
    执行
    0.46
    تباينه
    0.46
    振
    0.45
    ত্যাশিত
    0.43
    相
    0.43
    ഷ്ട്ര
    0.43
    POSITIVE LOGITS
    ವರು
    0.50
    ский
    0.49
     ਸ਼
    0.47
     Кра
    0.47
    episode
    0.46
    ადა
    0.46
     Gloss
    0.45
     GLOBAL
    0.45
     maan
    0.45
     episode
    0.45
    Activations Density 0.001%

    No Known Activations