© 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. 191108
    Prev
    Next
    INDEX
    Explanations

    fall unintentionally

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

    suppliers are

    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
    댁
    0.56
    壳
    0.55
    资产
    0.49
     appareils
    0.49
    而来
    0.49
    评价
    0.47
    shells
    0.47
    性价比
    0.46
    鸟
    0.46
    当店
    0.46
    POSITIVE LOGITS
    as
    0.52
     सहित
    0.47
     ²
    0.46
    to
    0.46
     Director
    0.45
     Henderson
    0.44
     dwie
    0.44
     Chief
    0.43
     sensitive
    0.43
    are
    0.42
    Activations Density 0.000%

    No Known Activations