© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 46138
    Prev
    Next
    INDEX
    Explanations

    贡献 影响 具体

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𒀀
    0.52
     منح
    0.49
    試料
    0.49
     curricula
    0.48
     উপকূল
    0.48
     이해
    0.46
    鳟
    0.45
    㤟
    0.45
    牞
    0.45
    秇
    0.45
    POSITIVE LOGITS
     dust
    0.46
    img
    0.43
    Immutable
    0.43
    isShow
    0.43
     embarrass
    0.43
    ój
    0.43
     ta
    0.42
     embarrassment
    0.41
     mirror
    0.41
    xz
    0.41
    Activations Density 0.007%

    No Known Activations