© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113912
    Prev
    Next
    INDEX
    Explanations

    medical terms and mathematical declarations

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

    scientific or medical terminology related to biological, chemical, or mathematical concepts.

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

    The neuron fires on uncommon, domain‐specific technical terms—especially long medical, scientific, or formula-related vocabulary.

    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
     内衣
    -3.25
    鱨
    -3.13
     ビキニ
    -3.13
     geschenk
    -2.73
     bilde
    -2.63
    ☑️
    -2.59
    ꪔ
    -2.59
     放題
    -2.58
    鴞
    -2.56
     帅气
    -2.55
    POSITIVE LOGITS
    [
    3.00
    }{
    2.81
     genauso
    2.72
     любого
    2.72
    ↵↵
    2.72
    <
    2.72
     другая
    2.72
           
    2.66
    The
    2.63
    <i>
    2.59
    Activations Density 0.035%

    No Known Activations