© 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. 10-GEMMASCOPE-RES-131K
    7. 105973
    Prev
    Next
    INDEX
    Explanations

    pandemic and administration actions

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

    references to pandemics, particularly COVID-19, and government administrations.

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

    The neuron is strongly activated by mentions of the pandemic—especially “pandemic” in the context of COVID-19—and related terms like “infection.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    -
    -1.48
    :
    -1.38
    >
    -1.31
     this
    -1.31
    z
    -1.29
     =
    -1.28
    id
    -1.27
    vers
    -1.26
    GLfloat
    -1.26
    нутри
    -1.24
    POSITIVE LOGITS
    νι
    1.67
     essentielle
    1.56
     hjälp
    1.52
     suena
    1.52
    ↵↵
    1.49
     you
    1.48
    thschild
    1.48
     eléctricas
    1.47
    Ostat
    1.46
     tráiler
    1.46
    Activations Density 0.009%

    No Known Activations