© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 10716
    Prev
    Next
    INDEX
    Explanations

    glucose, insulin, and diabetes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    лый
    0.47
    Boolean
    0.41
    ถา
    0.41
     лам
    0.40
    γωγ
    0.40
     וש
    0.39
     سانس
    0.39
    駝
    0.38
    ประชา
    0.38
     Coronation
    0.37
    POSITIVE LOGITS
     hypoglycemia
    0.88
     insulin
    0.86
     hypogly
    0.83
     diabetic
    0.79
    insulin
    0.76
     Insulin
    0.72
     diabetes
    0.71
     glucose
    0.71
    血糖
    0.68
     insulina
    0.67
    Activations Density 0.054%

    No Known Activations