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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 1863
    Prev
    Next
    INDEX
    Explanations

    diabetes and blood glucose

    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
     اسكت
    0.29
    เงิน
    0.28
    营业
    0.28
    ель
    0.27
     చేయడానికి
    0.27
     ముందుకు
    0.26
    蛞
    0.26
    衾
    0.26
    ეთ
    0.26
    브
    0.26
    POSITIVE LOGITS
     diabetes
    0.66
     Diabetes
    0.54
     glucose
    0.53
     diabetic
    0.52
     hypergly
    0.52
     hyperglycemia
    0.52
    diabetes
    0.52
     insulin
    0.51
    Diabetes
    0.48
     diabet
    0.48
    Activations Density 0.008%

    No Known Activations