© 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. 30898
    Prev
    Next
    INDEX
    Explanations

    people, patients, and children

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

    demographic details about study participants in medical research papers.

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

    This neuron detects quantitative study data, especially numerical counts (like sample sizes) and measurements often associated with “patients.”

    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
     hispan
    -0.93
     tulum
    -0.85
     Indon
    -0.85
    [@
    -0.84
    чений
    -0.83
     sés
    -0.82
     azule
    -0.79
    ignment
    -0.78
     granada
    -0.78
    QED
    -0.77
    POSITIVE LOGITS
     vínculo
    0.88
     precarious
    0.87
     núcleo
    0.81
     damskie
    0.80
     inserted
    0.79
     vínculos
    0.77
     convi
    0.77
    いただき
    0.75
     актри
    0.75
    Fuse
    0.75
    Activations Density 0.083%

    No Known Activations