© 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. 104524
    Prev
    Next
    INDEX
    Explanations

    symptoms

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

    medical symptoms and clinical manifestations listed in commas.

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

    The neuron strongly activates on tokens naming clinical symptoms (e.g., nausea, fever, cough, headache, diarrhea).

    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
     to
    -2.00
     our
    -1.89
     his
    -1.72
    v
    -1.70
     their
    -1.70
     it
    -1.70
    k
    -1.57
     the
    -1.54
    j
    -1.53
    s
    -1.50
    POSITIVE LOGITS
     or
    1.66
    ğim
    1.65
    ťaž
    1.62
     \&
    1.61
     moeilijk
    1.53
    不僅
    1.52
    jadwal
    1.51
    並不是
    1.46
     decoraciones
    1.44
    bước
    1.44
    Activations Density 0.131%

    No Known Activations