© 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. 40-GEMMASCOPE-2-RES-262K
    7. 36934
    Prev
    Next
    INDEX
    Explanations

    presentation slide elements

    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/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    elom
    0.45
    Კ
    0.44
    Ნ
    0.43
    Books
    0.40
    ein
    0.39
    իմ
    0.39
     кін
    0.39
    Გ
    0.39
     dut
    0.39
    determ
    0.39
    POSITIVE LOGITS
     briefly
    0.88
     слай
    0.80
     slide
    0.79
     slides
    0.76
     Slide
    0.72
     Slides
    0.71
     brief
    0.70
     présentée
    0.69
     소개
    0.68
     presenter
    0.67
    Activations Density 0.006%

    No Known Activations