© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65856
    Prev
    Next
    INDEX
    Explanations

    pandemics and health crises

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

    terms related to the COVID-19 pandemic, including references to the virus, health measures, and social impacts.

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

    The neuron is primarily detecting mentions of COVID-19 and related pandemic terminology.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ?
    -1.18
    :
    -1.02
     նաև
    -1.01
    $
    -1.00
    вѣ
    -0.94
    ANGES
    -0.94
     a
    -0.92
     también
    -0.92
    서
    -0.90
     $
    -0.88
    POSITIVE LOGITS
    年齡
    1.04
    zehn
    1.01
     soigne
    1.00
    adakan
    0.97
    hombres
    0.96
     memasang
    0.96
     hiyo
    0.95
    還在
    0.94
    hair
    0.94
    wesenheit
    0.93
    Activations Density 0.007%

    No Known Activations