© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 56777
    Prev
    Next
    INDEX
    Explanations

    page or Pager

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     sık
    0.43
     partitioned
    0.42
     брю
    0.41
     прото
    0.39
     бук
    0.39
     багато
    0.38
    酢
    0.38
     බෙ
    0.38
    
    0.38
     ethnic
    0.37
    POSITIVE LOGITS
    Pager
    0.70
    ViewPager
    0.67
     pager
    0.66
    pager
    0.66
    PagerAdapter
    0.59
    Page
    0.56
     PAGE
    0.54
    pagen
    0.54
    currentPage
    0.53
     Page
    0.50
    Activations Density 0.001%

    No Known Activations