© 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. 31-GEMMASCOPE-2-RES-262K
    7. 40822
    Prev
    Next
    INDEX
    Explanations

    programming, physics, economics, materials

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ವಿವರ
    0.50
     дуже
    0.49
     Архивная
    0.49
    叁章
    0.49
    Fred
    0.49
     ကြ
    0.48
     иска
    0.48
     ぞ
    0.48
    ianSpace
    0.48
     ў
    0.47
    POSITIVE LOGITS
    -
    0.52
     on
    0.46
     an
    0.44
    '
    0.44
    eran
    0.42
    araoh
    0.42
     nachos
    0.41
     Feed
    0.41
     permutations
    0.41
     Gravity
    0.40
    Activations Density 0.000%

    No Known Activations