© 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. 16-GEMMASCOPE-2-RES-65K
    7. 3782
    Prev
    Next
    INDEX
    Explanations

    based on the content

    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_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     display
    0.47
     lark
    0.47
     l
    0.47
    Lean
    0.46
     (
    0.45
     फिसल
    0.45
    Shuffle
    0.43
     barbeque
    0.43
    Cruise
    0.42
     barat
    0.42
    POSITIVE LOGITS
     الاول
    0.54
     الأول
    0.49
     заповед
    0.49
    }&=
    0.48
     Willing
    0.48
     Elektrokh
    0.47
    ensos
    0.47
    dgs
    0.47
     Primeiro
    0.46
    ন
    0.46
    Activations Density 0.000%

    No Known Activations