© 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. 453
    Prev
    Next
    INDEX
    Explanations

    coronavirus pandemic

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

    references to COVID-19 and coronavirus, including terms like "pandemic", "COVID-19", and various spellings of "coronavirus".

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

    The neuron detects mentions of the COVID-19 pandemic (e.g. “coronavirus,” “COVID-19,” “virus,” “pandemic”).

    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
    很重要
    -0.94
    ficha
    -0.92
     Gespräche
    -0.86
    samuel
    -0.86
    ့
    -0.85
    teaser
    -0.84
    Attempts
    -0.84
    Mvh
    -0.83
    sergio
    -0.82
    髂
    -0.81
    POSITIVE LOGITS
     pandemic
    1.83
     crisis
    1.52
     outbreak
    1.50
     lockdown
    1.41
     lockdowns
    1.24
     virus
    1.23
     restrictions
    1.21
     era
    1.20
     Covid
    1.17
     situation
    1.16
    Activations Density 0.006%

    No Known Activations