© 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. 14047
    Prev
    Next
    INDEX
    Explanations

    blood sugar and diabetes

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

    diabetes, glucose, insulin, blood sugar

    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
    អំពី
    0.50
    轵
    0.47
     procura
    0.47
     कॉनक
    0.45
    波動方程式
    0.45
     אחרי
    0.45
     Arkadaşlar
    0.44
     క్రికె
    0.44
    鸮
    0.44
    郆
    0.43
    POSITIVE LOGITS
     diabetes
    0.51
     insulin
    0.51
    os
    0.49
    sugar
    0.47
    path
    0.47
     sugar
    0.47
     Diabetes
    0.47
     glucose
    0.46
    diabetes
    0.46
    h
    0.46
    Activations Density 0.000%

    No Known Activations