© 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. 62090
    Prev
    Next
    INDEX
    Explanations

    service request download

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

    code context

    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
    壩
    0.61
     ਦਵਾਈ
    0.59
    鉋
    0.59
    藥
    0.56
    教師
    0.55
    圖像
    0.54
    曲線
    0.54
    動畫
    0.54
    兩個
    0.53
    ImgBoard
    0.53
    POSITIVE LOGITS
    is
    0.55
    ,
    0.52
    has
    0.49
     of
    0.49
     for
    0.48
    url
    0.48
     Bree
    0.48
     says
    0.48
     Mrs
    0.47
     Is
    0.46
    Activations Density 0.007%

    No Known Activations