© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 50393
    Prev
    Next
    INDEX
    Explanations

    pandemic and coronavirus events

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

    mentions of COVID-19, coronavirus pandemic, and related terminology.

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

    The neuron activates on numeric tokens, picking up years, dates, and other standalone numbers in the text.

    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
    Jacket
    -0.80
    菓
    -0.77
    categories
    -0.76
     пройдет
    -0.75
    Chara
    -0.73
     veulent
    -0.73
     fases
    -0.72
     afectado
    -0.71
    ilier
    -0.71
    vx
    -0.70
    POSITIVE LOGITS
     pandemic
    3.41
    pandemic
    1.94
     crisis
    1.93
     Pandemic
    1.62
     epidemic
    1.59
     coronavirus
    1.51
     pandemia
    1.48
     Pandemie
    1.47
     virus
    1.45
    疫情
    1.42
    Activations Density 0.018%

    No Known Activations