© 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. 3588
    Prev
    Next
    INDEX
    Explanations

    disease

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

    medical terms related to heart disease.

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

    The neuron is specialized to detect mentions of heart disease (especially phrases like “heart disease” or “coronary heart disease”).

    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
     to
    -1.94
     their
    -1.84
    .'
    -1.79
     我们
    -1.78
     They
    -1.73
     plethora
    -1.73
     vaguely
    -1.73
     mision
    -1.67
     eight
    -1.63
     achieves
    -1.55
    POSITIVE LOGITS
     kilos
    1.65
     aleación
    1.59
     aguja
    1.56
    0
    1.55
     spannende
    1.52
     firefighter
    1.50
     atentos
    1.50
    </b>
    1.49
    他
    1.45
     הוא
    1.44
    Activations Density 0.045%

    No Known Activations