© 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. 9151
    Prev
    Next
    INDEX
    Explanations

    health and healthcare services

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

    The neuron fires strongly on references to public‐health authorities, agencies, and official medical or vaccination guidelines.

    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
    unread
    0.58
     пациентов
    0.57
    LOY
    0.57
    Loy
    0.55
    valueOf
    0.54
    ATIVA
    0.54
    পৃথিব
    0.53
    狽
    0.53
     دین
    0.52
     কেন্দ্রীয়
    0.52
    POSITIVE LOGITS
     CDC
    1.30
    CDC
    1.05
     Epidemi
    0.98
     Epidemiology
    0.97
     Cdc
    0.97
     epidemi
    0.93
    cdc
    0.92
     Centers
    0.89
     Tobacco
    0.85
     epidemic
    0.84
    Activations Density 0.168%

    No Known Activations