© 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. 155454
    Prev
    Next
    INDEX
    Explanations

    planks, holding, or exercises

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

    focuses on individual skills and conflict

    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
    ين
    0.54
    ма
    0.53
    憨
    0.52
     Floren
    0.49
    马
    0.49
    臧
    0.49
    趵
    0.48
    苾
    0.48
    贝
    0.47
    抖
    0.47
    POSITIVE LOGITS
     مشکل
    0.50
     เชื่อ
    0.47
     زندگی
    0.45
     ಪುಸ್ತಕ
    0.45
     বই
    0.45
    joyed
    0.43
     عرصے
    0.43
     کف
    0.43
     کتاب
    0.42
     connection
    0.42
    Activations Density 0.002%

    No Known Activations