© 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. 117899
    Prev
    Next
    INDEX
    Explanations

    places and regions

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

    types of items and classifications

    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
    癤
    0.59
    𝗷
    0.58
     AWAY
    0.56
    😈
    0.52
    damn
    0.52
     OH
    0.52
    Damn
    0.52
    糞
    0.50
    MENT
    0.49
    減
    0.49
    POSITIVE LOGITS
     Gloucestershire
    0.51
     Macquarie
    0.47
     Lancashire
    0.47
     Gaelic
    0.46
     Macmillan
    0.46
    基础上
    0.46
    london
    0.46
     Warwickshire
    0.45
     Lincolnshire
    0.45
     Anglican
    0.44
    Activations Density 0.000%

    No Known Activations