© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77860
    Prev
    Next
    INDEX
    Explanations

    C-reactive protein inflammation

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

    laboratory and biochemical markers in medical research papers, particularly inflammatory markers like C-reactive protein.

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

    The neuron is specialized for detecting quantitative laboratory measurements and study data—numbers, units, and biomarker values.

    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
     vanil
    -0.74
    コウ
    -0.72
    Inverse
    -0.71
    吸引
    -0.70
     Inverse
    -0.70
     vart
    -0.69
     dile
    -0.68
     curi
    -0.68
     compan
    -0.68
     inverse
    -0.67
    POSITIVE LOGITS
     CRP
    1.84
    CRP
    1.55
     acute
    1.18
    acute
    1.07
     inflammation
    0.98
     Acute
    0.95
     inflammatory
    0.89
    inflammation
    0.85
     fibrin
    0.85
     Inflammation
    0.85
    Activations Density 0.094%

    No Known Activations