© 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. 108673
    Prev
    Next
    INDEX
    Explanations

    special characters and numbers

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

    tooling, school, extension, year, bears

    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
     DataSource
    0.47
     الخام
    0.47
     이러
    0.46
     遅
    0.46
     различни
    0.46
     المحدد
    0.46
     درجة
    0.45
     অনুস
    0.45
     FontSize
    0.44
     斜
    0.44
    POSITIVE LOGITS
    orov
    0.49
    ჯგუფი
    0.48
    Ᏸ
    0.47
    朝鲜
    0.45
    يل
    0.45
    উত্তর
    0.44
    Studies
    0.43
    اری
    0.43
    भारतीय
    0.43
    अप्रैल
    0.42
    Activations Density 0.001%

    No Known Activations