© 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. 79501
    Prev
    Next
    INDEX
    Explanations

    diseases and historical crises

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

    diseases and viruses like COVID-19, coronavirus, AIDS, Ebola, and HIV.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    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
    :"-
    -1.04
     COVID
    -0.97
     fuimos
    -0.92
     pandemia
    -0.91
     Kampagne
    -0.90
    Buona
    -0.88
     amélior
    -0.88
     sué
    -0.85
     lomba
    -0.84
    pompa
    -0.84
    POSITIVE LOGITS
     related
    1.14
     testing
    1.11
     tested
    1.06
     test
    1.04
     response
    1.03
     information
    0.97
    related
    0.97
    Related
    0.90
     era
    0.90
     specific
    0.89
    Activations Density 0.025%

    No Known Activations