© 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. 7216
    Prev
    Next
    INDEX
    Explanations

    brands and organizations

    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
     Vegetation
    0.32
    竝
    0.31
    colored
    0.30
    訥
    0.30
    vě
    0.29
    楪
    0.29
    createTextNode
    0.29
     immobilization
    0.28
     ln
    0.28
    ᄇ
    0.28
    POSITIVE LOGITS
    Instagram
    0.37
    Reuters
    0.34
     instagram
    0.34
     ilgi
    0.33
     lekker
    0.33
     Instagram
    0.32
     rugby
    0.32
     Lidl
    0.32
     delightfully
    0.31
     zase
    0.31
    Activations Density 2.401%

    No Known Activations