© 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. 98152
    Prev
    Next
    INDEX
    Explanations

    pandemic locations and numbers

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

    terms and phrases related to coronavirus/COVID-19.

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

    This neuron detects terms referring to the COVID-19 coronavirus (e.g. “coronavirus,” “COVID,” “virus,” “viral,” “outbreak,” “swept,” etc.).

    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
    甙
    -0.81
    ([^
    -0.80
     information
    -0.74
    Frosty
    -0.73
     russa
    -0.73
     ચ
    -0.72
    vito
    -0.71
     stay
    -0.68
     ulasan
    -0.67
     duration
    -0.66
    POSITIVE LOGITS
     cruise
    1.00
     Dae
    1.00
     Iran
    0.98
     Cruise
    0.84
    Iran
    0.84
    Cruise
    0.82
    UNTIME
    0.81
     Cheltenham
    0.80
     Ital
    0.77
    Fun
    0.76
    Activations Density 0.014%

    No Known Activations