© 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. 21709
    Prev
    Next
    INDEX
    Explanations

    做過, 也谈, 提法, 因小心, 变强, 引多, 打定, 测通, 听起来

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

    幫我, 没盾牌, 仅供

    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
     Thái
    0.60
     của
    0.56
    ோ
    0.56
     phiên
    0.56
     của
    0.55
     vật
    0.55
     hình
    0.54
     nước
    0.54
     tương
    0.54
     Châu
    0.54
    POSITIVE LOGITS
    Ο
    0.59
    下
    0.55
    在
    0.54
    看
    0.53
    Y
    0.52
    Ｕ
    0.49
    Ｌ
    0.48
    不过
    0.47
    需
    0.47
    无
    0.46
    Activations Density 0.002%

    No Known Activations