© 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. 10-GEMMASCOPE-RES-131K
    7. 66122
    Prev
    Next
    INDEX
    Explanations

    leading cause of death in the United States, Mexico, or Kenya

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

    mentions of "the United States" in medical or scientific publications.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron fires on mentions of “United States” (typically in statistical or epidemiological contexts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     one
    -2.55
     more
    -2.03
     their
    -1.82
     it
    -1.77
     what
    -1.69
     for
    -1.60
     at
    -1.59
     if
    -1.55
     as
    -1.55
     from
    -1.48
    POSITIVE LOGITS
    向了
    1.66
    因为他
    1.49
     temporaire
    1.48
    姈
    1.45
     perché
    1.41
    ferred
    1.38
    茈
    1.34
    volves
    1.33
     prides
    1.33
     любом
    1.32
    Activations Density 0.167%

    No Known Activations