© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78176
    Prev
    Next
    INDEX
    Explanations

    diabetes and insulin management

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

    medical content related to diabetes, including technical terms, studies, and treatments.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scheduler
    -0.86
    HPV
    -0.82
    XmlAccessorType
    -0.82
    dega
    -0.81
    Spotify
    -0.81
     HPV
    -0.78
     onBackPressed
    -0.77
    UFO
    -0.77
    秽
    -0.77
     Porn
    -0.76
    POSITIVE LOGITS
     diabetes
    3.81
     insulin
    3.50
     diabetic
    3.42
     Diabetes
    3.31
    Diabetes
    2.91
    insulin
    2.88
    diabetes
    2.84
     diabetics
    2.84
     Insulin
    2.80
     glucose
    2.75
    Activations Density 0.247%

    No Known Activations