© 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. 900
    Prev
    Next
    INDEX
    Explanations

    set theory

    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
     élytres
    0.69
    assaytype
    0.63
    繁忙時間服務
    0.62
     hydrolysis
    0.62
    lensFlare
    0.61
    ្នាំ
    0.61
    裄
    0.60
     partículas
    0.59
     স্তর
    0.59
    ナトリ
    0.59
    POSITIVE LOGITS
    in
    0.76
     Sets
    0.76
    set
    0.73
    n
    0.70
    Sets
    0.68
    S
    0.68
     sets
    0.65
    f
    0.65
    K
    0.65
     set
    0.64
    Activations Density 0.011%

    No Known Activations