© 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. 205328
    Prev
    Next
    INDEX
    Explanations

    product listings and suggestions

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

    explaining offensive words

    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
    参加
    0.53
    棹
    0.51
    आई
    0.48
    ordinated
    0.48
    Ки
    0.48
     रात्री
    0.48
    螓
    0.48
    ordination
    0.47
    ῳ
    0.47
    鰹
    0.47
    POSITIVE LOGITS
     involuntarily
    0.57
     eternally
    0.56
     distrust
    0.54
     unsettling
    0.52
     unconsciously
    0.51
     unsett
    0.50
     peacefully
    0.50
     belly
    0.50
     assassin
    0.50
     temporarily
    0.48
    Activations Density 0.001%

    No Known Activations