© 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. 10-GEMMASCOPE-RES-131K
    7. 11850
    Prev
    Next
    INDEX
    Explanations

    embolic events risk disease

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

    This neuron detects medical terms related to blood clots, thromboembolic conditions, and emboli.

    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_10/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
     he
    -2.36
    in
    -2.33
    ar
    -2.27
    o
    -2.16
    و
    -2.09
     intriguing
    -2.05
    l
    -2.03
     mesmerizing
    -1.98
    à
    -1.95
     startling
    -1.95
    POSITIVE LOGITS
    
    2.44
    𖥧
    2.31
    僊
    2.00
     незавер
    1.97
    涐
    1.84
    梘
    1.82
     November
    1.82
     verschill
    1.81
    韞
    1.79
    って思
    1.78
    Activations Density 0.030%

    No Known Activations