© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 60289
    Prev
    Next
    INDEX
    Explanations

    COVID and coronavirus

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

    COVID-19 severe illness death

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Behaviour
    0.47
     repeal
    0.45
    Margaret
    0.44
     repealed
    0.42
    🗺
    0.42
    毎年
    0.41
     المعادلات
    0.41
    Rat
    0.41
    酤
    0.41
     дости
    0.40
    POSITIVE LOGITS
     COVID
    0.94
     Covid
    0.88
     코로나
    0.88
     कोविड
    0.86
    covid
    0.82
    COVID
    0.81
     covid
    0.80
    新冠
    0.73
     coronavirus
    0.72
    Covid
    0.71
    Activations Density 0.009%

    No Known Activations