© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 100501
    Prev
    Next
    INDEX
    Explanations

    apple books, program, absolutely, shudder, durability, dangerous

    np_acts-logits-general · gemini-2.5-flash-lite

    historically

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鑼
    0.51
     ग
    0.50
    ए
    0.50
     教育
    0.49
     Đến
    0.48
     ኦ
    0.48
     下载
    0.48
     ట్రా
    0.46
     ए
    0.46
     tuba
    0.46
    POSITIVE LOGITS
    organisme
    0.48
    anek
    0.48
    一つの
    0.48
    あなたの
    0.47
    நபியே
    0.46
    iov
    0.46
    শন
    0.45
    separation
    0.44
    mys
    0.44
    mok
    0.44
    Activations Density 0.001%

    No Known Activations