© 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. 219977
    Prev
    Next
    INDEX
    Explanations

    research aims, integrate data

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

    names and multi-language greetings

    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
    江戸
    0.48
    善良
    0.48
    出身
    0.46
    憊
    0.46
    山东
    0.46
    損傷
    0.45
    ಾರ್ಟ
    0.45
    婇
    0.45
    ジル
    0.45
    대전
    0.44
    POSITIVE LOGITS
    เพิ่ม
    0.50
    llbracket
    0.49
    expand
    0.48
     बढ़े
    0.47
    iu
    0.46
    ynie
    0.45
    ino
    0.44
    expire
    0.43
    ėl
    0.43
    ineed
    0.43
    Activations Density 0.001%

    No Known Activations