© 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. 226470
    Prev
    Next
    INDEX
    Explanations

    assignment request or match

    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
    我不
    0.53
    Meet
    0.52
    Prepare
    0.50
    手臂
    0.50
    我已经
    0.49
    小时
    0.49
    勖
    0.49
    㚐
    0.48
    强调
    0.48
    陕西
    0.48
    POSITIVE LOGITS
    n
    0.54
     individual
    0.52
     beginnings
    0.50
     ф
    0.50
     records
    0.49
     anim
    0.49
     olds
    0.48
     record
    0.48
     f
    0.47
     forecasts
    0.47
    Activations Density 0.000%

    No Known Activations