© 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. 14781
    Prev
    Next
    INDEX
    Explanations

    public health epidemiology

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

    epidemiology and health studies

    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
     Gemä
    0.65
     Ultrasonic
    0.65
    鐏
    0.64
     مشتری
    0.63
    绚
    0.63
     Artist
    0.63
    机场
    0.62
     فیلم
    0.61
     artisti
    0.61
    辂
    0.60
    POSITIVE LOGITS
     epidemi
    1.53
    health
    1.39
     epidemiology
    1.38
     health
    1.37
     epidemiological
    1.34
     Epidemi
    1.23
    健康
    1.14
    epid
    1.10
     disease
    1.07
     स्वास्थ्य
    1.07
    Activations Density 0.108%

    No Known Activations