© 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. 10-GEMMASCOPE-RES-131K
    7. 73505
    Prev
    Next
    INDEX
    Explanations

    COVID-19 pandemic and coronavirus

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

    mentions of COVID-19, coronavirus, or pandemic-related terminology.

    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_10/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
    
    -1.66
     comienzo
    -1.58
     from
    -1.48
     the
    -1.46
    ⮚
    -1.45
    ();*/
    -1.45
    são
    -1.42
     themselves
    -1.42
     decent
    -1.40
     unui
    -1.39
    POSITIVE LOGITS
     Viejo
    1.36
    ってみました
    1.34
     Biro
    1.33
    inner
    1.30
    ≦
    1.29
     dispuestos
    1.28
     Penang
    1.27
    pe
    1.27
     problemet
    1.27
    activity
    1.27
    Activations Density 0.011%

    No Known Activations