© 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-65K
    7. 44817
    Prev
    Next
    INDEX
    Explanations

    Planet Made

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    InterfaceLine
    0.59
     עם
    0.56
     पेंसिल
    0.54
    ্ি
    0.52
     טי
    0.52
     ежедневно
    0.51
     עצ
    0.51
     任
    0.51
    Ა
    0.51
    <unused1813>
    0.51
    POSITIVE LOGITS
    (
    0.50
    1
    0.49
    \
    0.48
    Stadt
    0.47
    ’
    0.47
     dam
    0.45
    Russian
    0.44
    public
    0.43
    aw
    0.43
    Soviet
    0.43
    Activations Density 0.006%

    No Known Activations