© 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. 123655
    Prev
    Next
    INDEX
    Explanations

    herbal remedies and drinks

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

    The neuron activates strongly for the word "herbal" or variations like "herbalist" when describing natural remedies, supplements, and medicines.

    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
     "
    -2.94
    ↵
    -2.86
     ''
    -2.73
     {
    -2.59
    o
    -2.41
     '
    -2.39
    {
    -2.34
     ``
    -2.33
     姆
    -2.30
    ‌هایی
    -2.28
    POSITIVE LOGITS
    lgari
    2.97
     Mainly
    2.78
     Ráp
    2.73
    ܊
    2.73
    elerik
    2.72
     Nonetheless
    2.66
     Also
    2.58
     Здесь
    2.55
     Somewhat
    2.52
     männer
    2.42
    Activations Density 0.002%

    No Known Activations