© 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. 237838
    Prev
    Next
    INDEX
    Explanations

    sentence endings, conjunctions, or connecting phrases

    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
    حم
    0.50
    利用
    0.45
    贡献
    0.44
    عل
    0.44
    第一次
    0.43
    最
    0.43
    作者
    0.43
    Authorization
    0.43
    ت
    0.43
    جم
    0.43
    POSITIVE LOGITS
    の後
    0.60
     後
    0.56
     そして
    0.55
    ಾರೆ
    0.54
     及び
    0.54
     Portanto
    0.54
     နှင့်
    0.53
     პირადი
    0.52
     へ
    0.52
     やっ
    0.52
    Activations Density 0.000%

    No Known Activations