© 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. 198303
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific usages

    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
     ಕಾ
    0.42
    䚯
    0.38
    strel
    0.38
    ള്‍
    0.38
    يران
    0.37
     पली
    0.37
     Gam
    0.36
     बांग
    0.36
     Snowflake
    0.36
     trow
    0.35
    POSITIVE LOGITS
     ppb
    0.43
     zuerst
    0.40
    先
    0.39
    首先
    0.38
    svg
    0.37
    漉
    0.37
    ملك
    0.36
    Же
    0.36
    財布
    0.36
     toujours
    0.35
    Activations Density 0.004%

    No Known Activations