© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 9185
    Prev
    Next
    INDEX
    Explanations

    code fragments and identifiers

    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
    ishment
    0.29
    println
    0.28
    print
    0.26
     prints
    0.26
    ########
    0.25
    ↵↵↵↵
    0.25
    туры
    0.25
    ennials
    0.25
    pronounced
    0.25
    へと
    0.24
    POSITIVE LOGITS
     මෙ
    0.35
     ഈ
    0.30
    temp
    0.29
    șt
    0.29
    兟
    0.29
     टेंपरे
    0.29
     ০১
    0.29
     tmp
    0.29
    ০
    0.29
    峀
    0.29
    Activations Density 0.001%

    No Known Activations