© 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. 17912
    Prev
    Next
    INDEX
    Explanations

    along

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

    beyond the ordinary

    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
    アプリケーション
    0.57
     Rodriguez
    0.50
     viv
    0.49
    従業
    0.49
     ポイント
    0.48
    츨
    0.48
     Кор
    0.48
     Генера
    0.47
     グ
    0.47
     fuh
    0.47
    POSITIVE LOGITS
    arı
    0.54
    stantially
    0.44
     stepwise
    0.41
    吗
    0.41
    看着
    0.39
    找到
    0.39
    ovaných
    0.38
    Reform
    0.38
    veled
    0.38
    的变化
    0.37
    Activations Density 0.000%

    No Known Activations