© 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. 122770
    Prev
    Next
    INDEX
    Explanations

    old books and permitted trades

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

    older documents, historical contexts

    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
    鋁
    0.41
     እንቅስቃሴ
    0.41
     রাজধানীতে
    0.39
    福岡
    0.39
     salen
    0.39
    渕
    0.39
     Số
    0.38
     ফল
    0.38
     véh
    0.38
     FACE
    0.38
    POSITIVE LOGITS
    纪
    0.49
    หน่อย
    0.47
    ლებიც
    0.47
    𓂀
    0.46
    шинство
    0.44
    再加上
    0.43
    nač
    0.43
     konfigur
    0.43
     सेटअप
    0.43
    瑟
    0.43
    Activations Density 0.001%

    No Known Activations