© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79260
    Prev
    Next
    INDEX
    Explanations

    diseases and causes

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

    lists of medical conditions in academic medical texts.

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

    The neuron flags specialized medical terminology describing disease processes or pathological conditions (e.g. terms like “thrombotic,” “disorders,” “syndrome,” etc.).

    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
     tachycardia
    -0.88
     janu
    -0.85
    rillation
    -0.85
     ἀ
    -0.84
    FRANC
    -0.84
    お肉
    -0.84
    ============
    -0.83
    撿
    -0.82
    QMessageBox
    -0.82
     ἐ
    -0.80
    POSITIVE LOGITS
     trauma
    1.27
     malignancy
    1.05
     extensive
    1.01
     deliberate
    1.00
    trauma
    0.98
     long
    0.97
     states
    0.96
     any
    0.96
     burns
    0.96
     Trauma
    0.94
    Activations Density 0.443%

    No Known Activations