© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25937
    Prev
    Next
    INDEX
    Explanations

    drug names and medical terms

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

    mentions of medications, drugs, or medical/pharmaceutical terminology.

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

    The neuron activates on mentions of medications or drugs and related terms (e.g., prescribing, taking, pills, medical purpose).

    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
    }=$
    -0.91
     Medical
    -0.87
    лля
    -0.86
     solely
    -0.83
    rometer
    -0.82
    くん
    -0.81
    кота
    -0.78
    Norma
    -0.77
    ➪
    -0.76
    uesas
    -0.76
    POSITIVE LOGITS
     that
    1.09
     names
    0.90
     início
    0.88
     televisión
    0.88
    begins
    0.87
    ༷
    0.87
     side
    0.86
    ໊
    0.85
     começa
    0.84
     prisão
    0.84
    Activations Density 0.004%

    No Known Activations