© 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. 73510
    Prev
    Next
    INDEX
    Explanations

    medical terms and conditions

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

    medical terms and scientific language in clinical studies or medical case reports.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron activates on numerical tokens, i.e. digits and measurements (quantities, counts, dosages, percentages) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     chré
    -1.02
     teş
    -0.98
    Btw
    -0.96
     inconce
    -0.96
     Meiji
    -0.95
     malady
    -0.94
    Doctoral
    -0.93
     maladies
    -0.93
     behavi
    -0.92
     foret
    -0.90
    POSITIVE LOGITS
    
    1.07
    DISCUSSION
    1.00
     frank
    1.00
    ֶּ
    0.96
     presentation
    0.96
     valg
    0.90
     classic
    0.88
    Ethics
    0.87
     picture
    0.87
    rašymas
    0.86
    Activations Density 0.604%

    No Known Activations