© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 643
    Prev
    Next
    INDEX
    Explanations

    pun, wordplay cases

    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
    ាតុ
    0.57
    ه‌ها
    0.55
    繁忙時間服務
    0.51
     এইরূপে
    0.49
     അതു
    0.48
     identique
    0.48
    ាត់
    0.48
    <unused706>
    0.47
    <unused25>
    0.47
     zelen
    0.47
    POSITIVE LOGITS
    re
    0.52
    er
    0.50
    in
    0.50
    on
    0.50
    לי
    0.49
    p
    0.49
    en
    0.48
    k
    0.48
     on
    0.47
    쁘
    0.46
    Activations Density 0.006%

    No Known Activations