© 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. 6255
    Prev
    Next
    INDEX
    Explanations

    numbers in parentheses or lists

    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
     suatu
    0.35
    邙
    0.32
     Ducati
    0.32
     ciertos
    0.31
     কোনও
    0.31
     خفیہ
    0.31
     Seorang
    0.31
    쌈
    0.31
    啐
    0.30
     일부
    0.29
    POSITIVE LOGITS
     копия
    0.36
    ຂໍ້ມ
    0.34
    ingan
    0.34
    organisms
    0.34
    ка
    0.34
     beings
    0.33
    same
    0.33
    ITIONAL
    0.33
     كند
    0.33
    など
    0.32
    Activations Density 0.000%

    No Known Activations