© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 25311
    Prev
    Next
    INDEX
    Explanations

    non-English words and characters

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ᔾ
    0.47
    紆
    0.43
     ’’
    0.43
     «
    0.40
     "%
    0.40
     autem
    0.40
     hypothalamic
    0.40
    =","><
    0.40
    \<^
    0.39
     IERC
    0.39
    POSITIVE LOGITS
     ውሃ
    0.46
    饮料
    0.40
     ग्लास
    0.39
    MINUTE
    0.39
     februar
    0.38
     februari
    0.38
    ອາຫານ
    0.37
    ทะเล
    0.37
     청바
    0.37
     ตุลาคม
    0.37
    Activations Density 0.017%

    No Known Activations