© 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. 799
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is find detailed descriptions of medical conditions, injuries, symptoms, and related bodily or health events.

    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
     nouve
    0.70
     ಅವು
    0.69
     gemüt
    0.68
    omenclature
    0.68
     juicy
    0.66
     Fintech
    0.66
    😎
    0.65
    🏛
    0.64
     ассорти
    0.64
     diversité
    0.64
    POSITIVE LOGITS
     medically
    2.13
     hospitalization
    2.13
     hospital
    2.11
     medical
    2.03
    病情
    2.02
     doctors
    2.00
     hospitalized
    1.95
     médecins
    1.89
     치료
    1.88
     بیمار
    1.87
    Activations Density 1.686%

    No Known Activations