© 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. 307
    Prev
    Next
    INDEX
    Explanations

    COVID-19 testing

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

    dates and timestamps in formal documents and news articles.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    uate
    -0.74
     الث
    -0.72
     allergens
    -0.71
     según
    -0.68
     ديسمبر
    -0.66
    onStop
    -0.66
    漬け
    -0.66
    埜
    -0.66
     гла
    -0.65
     نوفمبر
    -0.65
    POSITIVE LOGITS
     Testing
    1.13
    Testing
    1.11
     testing
    1.01
     COVID
    1.00
     Coronavirus
    0.95
     TESTING
    0.89
    samples
    0.89
     WHO
    0.89
     Covid
    0.88
    Restriction
    0.88
    Activations Density 0.006%

    No Known Activations