© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7707
    Prev
    Next
    INDEX
    Explanations

    medical concepts and practices

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

    The neuron fires on occurrences of the word “medical” (and closely related professional‐health terms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    妲
    0.57
     dinner
    0.55
     தாய
    0.55
     extrapolated
    0.53
     girlfriend
    0.52
     Ery
    0.52
    த்திர
    0.52
    巴
    0.52
     waterslide
    0.52
    рки
    0.51
    POSITIVE LOGITS
     assistenza
    0.68
    pls
    0.66
    윌
    0.66
    imagery
    0.66
    MEDICAL
    0.64
    jorie
    0.64
    ⚕
    0.63
    imaging
    0.61
     med
    0.61
    terminology
    0.61
    Activations Density 0.131%

    No Known Activations