© 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. 9795
    Prev
    Next
    INDEX
    Explanations

    medications and drugs

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

    This neuron detects mentions of medical treatments or interventions (especially medications and therapies).

    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
     velvety
    0.62
     torsional
    0.57
     रूई
    0.56
     mkdir
    0.55
     beaches
    0.55
     workmanship
    0.54
    粘
    0.54
     textural
    0.54
     satisfactory
    0.53
    ខ្ល
    0.53
    POSITIVE LOGITS
     medication
    1.98
     medications
    1.96
     drugs
    1.83
     Medication
    1.77
     pharmaceuticals
    1.72
     Medications
    1.71
    藥
    1.71
     meds
    1.70
    drugs
    1.66
     лекар
    1.66
    Activations Density 0.379%

    No Known Activations