© 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. 63567
    Prev
    Next
    INDEX
    Explanations

    King James Version

    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
     incarn
    0.42
    aman
    0.38
     Christians
    0.38
    ecirc
    0.38
     הס
    0.37
    හා
    0.37
     נ
    0.37
     اطراف
    0.37
    `
    0.37
     umbilical
    0.36
    POSITIVE LOGITS
     Updated
    0.46
     kj
    0.42
     king
    0.42
     আপডেট
    0.42
     King
    0.42
    King
    0.41
     الملك
    0.40
     Update
    0.38
     KJ
    0.38
     Study
    0.38
    Activations Density 0.001%

    No Known Activations