© 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. 10-GEMMASCOPE-RES-131K
    7. 9274
    Prev
    Next
    INDEX
    Explanations

    paramedics and medics

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

    The neuron activates on medical practitioners such as paramedics, medics, and physicians.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ).
    -2.83
    });
    -2.61
    ");
    -2.50
    }{
    -2.47
    ());
    -2.33
     esoteric
    -2.30
    ');
    -2.27
    🗹
    -2.23
    」
    -2.23
    .”
    -2.23
    POSITIVE LOGITS
    狆
    2.56
     faſt
    2.52
    鼉
    2.45
    甞
    2.34
    却不
    2.27
     sona
    2.16
     vicini
    2.11
    
    2.11
     heo
    2.08
    畱
    2.05
    Activations Density 0.007%

    No Known Activations