© 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. 634
    Prev
    Next
    INDEX
    Explanations

    programming constructs

    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
    ើន
    0.35
    <unused1086>
    0.34
    ាតុ
    0.33
    َان
    0.33
    phthalm
    0.32
    <unused1053>
    0.32
    idential
    0.32
    ススメ
    0.32
    <unused582>
    0.32
    searchDisplay
    0.32
    POSITIVE LOGITS
     on
    0.36
     бушлай
    0.36
     via
    0.35
    in
    0.34
    에
    0.34
     to
    0.33
     Financ
    0.32
     호출
    0.32
    인
    0.32
     in
    0.31
    Activations Density 0.035%

    No Known Activations