© 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. 26533
    Prev
    Next
    INDEX
    Explanations

    universal

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

    universal applications and concepts

    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
    分裂
    0.52
     gön
    0.48
    的多
    0.47
    多彩
    0.46
    羡
    0.46
    ைகளால்
    0.46
     разно
    0.45
    感的
    0.45
    s
    0.45
     кад
    0.45
    POSITIVE LOGITS
     universal
    1.14
    Universal
    1.11
     Universal
    1.05
     universally
    1.00
    universal
    0.97
     универса
    0.82
     यूनिवर्सल
    0.78
     UNIVERS
    0.77
     universality
    0.72
    通用
    0.69
    Activations Density 0.017%

    No Known Activations