© 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. 200252
    Prev
    Next
    INDEX
    Explanations

    end punctuation and formatting

    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
    itecture
    0.46
    这个问题
    0.45
    <0xA9>
    0.43
    感受
    0.41
    -
    0.41
    세를
    0.40
    andering
    0.39
    技术的
    0.39
    <0x88>
    0.39
    Cage
    0.39
    POSITIVE LOGITS
     tarz
    0.52
    𝚃
    0.51
     disapproved
    0.50
     Mannschaften
    0.50
     potongan
    0.50
     blames
    0.49
    𝒕
    0.49
     develop
    0.48
     inactivity
    0.47
     increases
    0.47
    Activations Density 0.002%

    No Known Activations