© 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. 26919
    Prev
    Next
    INDEX
    Explanations

    start project

    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
     Jockey
    0.40
     ارز
    0.38
     dom
    0.38
    tev
    0.38
     コード
    0.38
    問い合わせ
    0.38
    WindowClass
    0.37
     Waterman
    0.36
    cyte
    0.36
    售
    0.36
    POSITIVE LOGITS
     skin
    0.44
     кожа
    0.43
     skins
    0.42
    isVisible
    0.42
     Skin
    0.41
    皮肤
    0.41
    肌肤
    0.39
     bruising
    0.39
     жесто
    0.39
     Skins
    0.39
    Activations Density 0.014%

    No Known Activations