© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 45561
    Prev
    Next
    INDEX
    Explanations

    GLP-1 receptor agonists and diabetes drugs

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

    medical and pharmaceutical terminology related to diabetes medications 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
     ralla
    -0.74
     terima
    -0.74
    erva
    -0.73
    ෂ
    -0.73
     Empirical
    -0.71
    頜
    -0.71
    ঠ
    -0.71
     ocup
    -0.69
     empirical
    -0.68
     phénom
    -0.68
    POSITIVE LOGITS
     GLP
    1.48
    GLP
    1.21
     DPP
    1.15
     sulfon
    1.09
    Diabetes
    1.02
     met
    1.01
     Met
    1.00
     pio
    0.99
     glit
    0.96
     Pio
    0.95
    Activations Density 0.148%

    No Known Activations