© 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. 14622
    Prev
    Next
    INDEX
    Explanations

    Wuhan, Hubei, Italy, COVID-19

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

    references to COVID-19 and related medical terms, locations, and healthcare contexts.

    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
     velocidades
    -1.27
    warzys
    -1.23
    inheit
    -1.23
    Republicans
    -1.19
     motores
    -1.19
     tahun
    -1.12
    ModelAndView
    -1.11
    eddah
    -1.11
     גם
    -1.10
     arquite
    -1.10
    POSITIVE LOGITS
    T
    1.23
     обеспечение
    1.17
    ac
    1.17
    回到了
    1.16
    最後は
    1.13
     насељу
    1.13
    又一次
    1.12
    9
    1.11
    各大
    1.11
    F
    1.10
    Activations Density 0.025%

    No Known Activations