© 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. 65632
    Prev
    Next
    INDEX
    Explanations

    myocardial infarction and damage

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

    The neuron detects mentions of 'myocardial' in cardiac/heart-related medical text.

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

    The neuron strongly activates on medical terms containing the “myocard-” root (e.g. myocardium, myocardial), i.e., references to heart muscle.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    та
    -2.97
    or
    -2.80
    ва
    -2.78
    i
    -2.75
    s
    -2.73
    and
    -2.72
    e
    -2.67
    if
    -2.48
    </h3>
    -2.41
    -
    -2.41
    POSITIVE LOGITS
    LETIN
    2.66
    尨
    2.58
    ༵
    2.39
    푆
    2.30
    ꪔ
    2.28
    UGHTER
    2.27
    
    2.23
    鉝
    2.19
    ญี่ป
    2.17
     Estamos
    2.16
    Activations Density 0.004%

    No Known Activations