© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 185117
    Prev
    Next
    INDEX
    Explanations

    colors and descriptions

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

    day passes or weekend

    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
    Negative Logits
    蚂
    0.52
    이
    0.50
    定义
    0.50
    意义
    0.50
    ρύ
    0.49
    为
    0.49
    攻击
    0.47
     any
    0.47
    对
    0.47
    自我
    0.46
    POSITIVE LOGITS
     reddish
    0.56
     તમને
    0.55
     کم
    0.50
     bluish
    0.48
     isopropyl
    0.48
    雑貨
    0.47
     brownish
    0.47
     reckless
    0.45
     rebuke
    0.44
    idamente
    0.44
    Activations Density 0.000%

    No Known Activations