© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116142
    Prev
    Next
    INDEX
    Explanations

    pathology and diagnostic challenge

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

    medical/scientific terminology related to pathology and physiology.

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

    This neuron fires on Greek‐derived medical or clinical terminology (“patho,” “physio,” “diagnostic,” “sign,” etc.), i.e. roots and affixes common in medical jargon.

    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
     печень
    -0.74
    னை
    -0.72
    餡
    -0.70
    グラフ
    -0.69
     Weinberg
    -0.68
    Dining
    -0.67
    нове
    -0.67
    llung
    -0.66
     läh
    -0.65
    displaystyle
    -0.65
    POSITIVE LOGITS
     patho
    1.38
    gn
    1.21
     physio
    1.08
     gn
    1.02
     diagnostic
    0.99
     peculiar
    0.97
    ogno
    0.81
    diagnostic
    0.80
     Physio
    0.80
     characteristic
    0.80
    Activations Density 0.075%

    No Known Activations