© 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. 39469
    Prev
    Next
    INDEX
    Explanations

    pneumonia

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

    references to "pneumonia" in medical and research 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
    *
    -2.86
    他的
    -2.86
     quando
    -2.80
    在我
    -2.70
     They
    -2.69
    ”
    -2.67
    0
    -2.66
    6
    -2.64
    .”
    -2.63
     cuando
    -2.63
    POSITIVE LOGITS
     gustaMe
    2.72
     estí
    2.48
     oficinas
    2.41
     motocicletas
    2.36
    鞴
    2.31
    鑁
    2.30
     significados
    2.28
     elástico
    2.28
     that
    2.27
     mußte
    2.25
    Activations Density 0.006%

    No Known Activations