© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16658
    Prev
    Next
    INDEX
    Explanations

    vaccines, drugs, and companies

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

    medical terminology related to vaccines and pharmaceutical products.

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

    The neuron fires on mentions of medical interventions—drug or vaccine names (often flagged as “experimental”), dosage‐related terms, or treatment labels.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Theologie
    -1.48
     chré
    -1.45
    皈
    -1.28
    通常
    -1.22
     eſt
    -1.16
    月は
    -1.15
     стихотво
    -1.14
     cristianos
    -1.12
     ſi
    -1.11
    ׇ
    -1.11
    POSITIVE LOGITS
    ּוֹ
    1.66
    ַּ
    1.64
    ְּ
    1.48
    اقرأ
    1.41
    ִּ
    1.41
    hichever
    1.40
    אַ
    1.38
    actéristiques
    1.38
     сообщили
    1.35
    цкого
    1.32
    Activations Density 0.004%

    No Known Activations