© 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. 197605
    Prev
    Next
    INDEX
    Explanations

    words associated with administration and law

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

    account management or gaming

    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
     entr
    0.55
     gelas
    0.50
     tóc
    0.49
     点
    0.49
     formé
    0.48
     lia
    0.47
     OPP
    0.47
     ধ্ব
    0.46
     Loew
    0.45
     TOE
    0.44
    POSITIVE LOGITS
    新增
    0.49
    ه‌ها
    0.48
    薮
    0.46
    答案
    0.46
    ಿ
    0.46
    즈
    0.45
    管理人
    0.44
    克兰
    0.43
    ogu
    0.42
    éu
    0.42
    Activations Density 0.002%

    No Known Activations