© 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. 11663
    Prev
    Next
    INDEX
    Explanations

    data and logic processing

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

    data processing and states

    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
     negros
    0.73
     mahogany
    0.63
    詩
    0.61
     فلم
    0.60
     impregnation
    0.59
     плен
    0.59
     iskol
    0.58
    鴛
    0.56
     патри
    0.56
     гимна
    0.56
    POSITIVE LOGITS
     Middleware
    1.00
    数据
    0.95
    存储
    0.95
     deserial
    0.93
     Data
    0.91
    数据的
    0.91
     数据
    0.88
     middleware
    0.83
     data
    0.82
    逻辑
    0.82
    Activations Density 0.148%

    No Known Activations