© 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. 10472
    Prev
    Next
    INDEX
    Explanations

    steps rather than

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

    rather than / one at a time

    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
    ச்சே
    0.40
    _
    0.39
    ･
    0.38
    例文帳に追加
    0.38
     interstices
    0.38
    員の
    0.38
     constituted
    0.37
     afternoon
    0.37
    等の
    0.37
    તુ
    0.37
    POSITIVE LOGITS
     álgebra
    0.54
    简化
    0.54
    骡
    0.49
    攻击
    0.49
     einfacher
    0.49
     제곱
    0.48
    Simplified
    0.47
    Subtraction
    0.47
     ошибки
    0.46
    镜头
    0.46
    Activations Density 0.000%

    No Known Activations