© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 64569
    Prev
    Next
    INDEX
    Explanations

    enzyme replacement therapy

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

    This neuron detects terms related to genetic disorders and rare diseases, particularly lysosomal storage disorders like Gaucher Disease and Tay-Sachs Disease.

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

    The neuron is selectively activating on specialized biomedical and genetic terminology—particularly gene names, mutations, and molecular biomarkers in medical research contexts.

    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
     Cancer
    -0.82
     després
    -0.80
     alcohol
    -0.80
     cancer
    -0.78
     perquè
    -0.77
    Preset
    -0.71
    īts
    -0.71
     alcoholic
    -0.69
    weise
    -0.68
    贷款
    -0.68
    POSITIVE LOGITS
     enzyme
    1.21
    Enzyme
    1.13
     Enzyme
    1.11
     lys
    0.99
     correction
    0.98
     substrate
    0.97
    enzyme
    0.96
     fibroblasts
    0.96
     Substrate
    0.90
     corrects
    0.84
    Activations Density 0.102%

    No Known Activations