© 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. 99230
    Prev
    Next
    INDEX
    Explanations

    doctor performs recommendations

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

    references to doctors, medical professionals, and medical diagnoses or treatments.

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

    The neuron activates when the text refers to medical professionals or authoritative health‐care figures (e.g. “doctor,” “Dr.,” “cardiologist,” “expert,” “physicians”).

    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
    wies
    -0.89
    eteria
    -0.84
     consommate
    -0.82
     connus
    -0.79
    Ǩ
    -0.77
    zini
    -0.77
     receber
    -0.77
     recieved
    -0.76
    druck
    -0.76
    arini
    -0.76
    POSITIVE LOGITS
     perform
    1.81
     performing
    1.80
     recommend
    1.59
     performed
    1.58
    perform
    1.54
     performs
    1.48
    Performing
    1.44
    Perform
    1.43
     Perform
    1.31
     recommended
    1.29
    Activations Density 0.034%

    No Known Activations