© 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-262K
    7. 128023
    Prev
    Next
    INDEX
    Explanations

    programming, cities, tables, sharing

    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_262k_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
    身体
    0.50
    珴
    0.49
    パフォーマンス
    0.49
    성과
    0.45
    後ろ
    0.43
    男朋友
    0.43
    편
    0.42
     rolled
    0.42
    同学
    0.42
    وسی
    0.41
    POSITIVE LOGITS
    uk
    0.52
    Fy
    0.48
     Angkor
    0.48
    f
    0.47
    ke
    0.47
    stä
    0.46
    b
    0.46
    граф
    0.46
    KN
    0.45
    akov
    0.44
    Activations Density 0.002%

    No Known Activations