© 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. 114002
    Prev
    Next
    INDEX
    Explanations

    low back pain

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

    units of measurement and dimensional terms.

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

    The neuron fires on low‐frequency “content” tokens—uncommon nouns, adjectives, units, and technical terms—rather than on common function words.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    cestry
    -1.45
     lorsque
    -1.42
     frança
    -1.38
    搋
    -1.37
    hanced
    -1.34
     geolog
    -1.33
     labi
    -1.32
    ONAUT
    -1.32
     westfalen
    -1.30
     menaces
    -1.30
    POSITIVE LOGITS
     for
    1.87
     of
    1.73
    ”,
    1.72
     has
    1.63
     over
    1.62
     take
    1.61
    čů
    1.61
     time
    1.59
     even
    1.54
     Even
    1.54
    Activations Density 0.099%

    No Known Activations