© 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. 2921
    Prev
    Next
    INDEX
    Explanations

    summaries and descriptions

    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
    ส
    0.34
    ิ
    0.33
    ี
    0.33
    ൪
    0.33
    จ
    0.31
     וי
    0.30
    ೧
    0.30
     використову
    0.30
    ฟ
    0.30
    ถ้า
    0.30
    POSITIVE LOGITS
     governance
    0.32
     messaging
    0.29
     outlier
    0.29
     spokesperson
    0.29
     nonprofits
    0.29
     regulatory
    0.28
     hasn
    0.28
     vaping
    0.28
     nonprofit
    0.27
     Coordinator
    0.27
    Activations Density 0.249%

    No Known Activations