© 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. 193217
    Prev
    Next
    INDEX
    Explanations

    charity events

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

    CPM technique

    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
    柯
    0.52
    远
    0.50
    贯
    0.49
    舘
    0.48
    嘎
    0.47
    跨
    0.47
    可靠
    0.46
    西班牙
    0.46
    缓存
    0.46
    格局
    0.46
    POSITIVE LOGITS
    ’
    0.49
     wsp
    0.46
    reduced
    0.45
    rya
    0.44
     nghệ
    0.44
     attendants
    0.44
    Reduced
    0.44
     numero
    0.43
     attendant
    0.42
    staande
    0.42
    Activations Density 0.001%

    No Known Activations