© 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. 15571
    Prev
    Next
    INDEX
    Explanations

    along a path

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

    The neuron detects phrases describing movement or extension “along” some physical feature (e.g. a riverbank, road, or trail).

    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
    
    -1.71
    ladelphia
    -1.70
     antaranya
    -1.68
     Irán
    -1.66
    椟
    -1.65
    푣
    -1.59
    沵
    -1.59
     Webinar
    -1.56
    тил
    -1.55
     semanal
    -1.55
    POSITIVE LOGITS
     the
    3.23
    -
    2.02
     for
    1.88
    f
    1.85
     [
    1.69
     to
    1.66
    ations
    1.63
    ll
    1.63
    i
    1.60
     To
    1.59
    Activations Density 0.024%

    No Known Activations