© 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. 41-GEMMASCOPE-2-RES-262K
    7. 9409
    Prev
    Next
    INDEX
    Explanations

    acronyms

    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
    Negative Logits
    জনের
    0.44
    َي
    0.43
    えています
    0.43
    ratingBarStyle
    0.42
     xử
    0.41
    白色
    0.41
    ิ
    0.40
     gebru
    0.40
    ром
    0.40
    izers
    0.40
    POSITIVE LOGITS
    s
    0.52
    As
    0.49
    Ps
    0.48
    Ws
    0.46
    f
    0.46
    Fa
    0.43
    ಗಳಿಗೆ
    0.43
    Ms
    0.42
    Os
    0.39
    Gs
    0.39
    Activations Density 0.024%

    No Known Activations