© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56814
    Prev
    Next
    INDEX
    Explanations

    severe health complications

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

    references to COVID-19 and coronavirus infections, including symptoms, treatments, and clinical data.

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

    The main thing this neuron does is detect numerical statistics and counts (e.g. numbers, percentages, and numeric measurements) in scientific or medical text.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    reducible
    -0.81
    糜
    -0.77
    几年
    -0.77
     christlichen
    -0.77
    ambiental
    -0.76
    ｙ
    -0.75
    áli
    -0.75
     cosmetic
    -0.75
     eſt
    -0.75
    Brainz
    -0.74
    POSITIVE LOGITS
     COVID
    2.83
     Covid
    2.52
     covid
    2.30
    COVID
    2.28
     coronavirus
    2.19
     SARS
    2.11
    covid
    2.08
     Coronavirus
    2.06
    Covid
    2.06
    Coronavirus
    1.74
    Activations Density 0.058%

    No Known Activations