© 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. 22-GEMMASCOPE-RES-131K
    7. 25016
    Prev
    Next
    INDEX
    Explanations

    matching pairs or complementary connections

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

    The neuron identifies technical terms that denote physical or electronic connection points—e.g. contacts, connectors, sockets, and coupling.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     دقیقه
    -0.90
     accumulation
    -0.83
     hã
    -0.80
     inclusion
    -0.77
    bourg
    -0.76
    FlatAppearance
    -0.75
    endipity
    -0.74
    msec
    -0.74
     merkezi
    -0.74
    ってみ
    -0.74
    POSITIVE LOGITS
     matching
    2.22
    matching
    1.86
    Matching
    1.80
     match
    1.77
     matched
    1.70
    匹配
    1.70
     Matching
    1.66
    match
    1.62
     counterpart
    1.52
     MATCH
    1.50
    Activations Density 0.220%

    No Known Activations