© 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. 68706
    Prev
    Next
    INDEX
    Explanations

    network bandwidth and capacity

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

    The neuron consistently activates on technical terms denoting network throughput or capacity (e.g. “bandwidth,” “capacity,” “utilization,” “load”).

    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
    、“
    -1.65
     bulu
    -1.59
     ekor
    -1.48
     ſaid
    -1.47
     tebal
    -1.45
    ֍
    -1.45
     quadrinhos
    -1.44
     pembe
    -1.43
     gantung
    -1.41
     sekunder
    -1.41
    POSITIVE LOGITS
    between
    1.54
    0
    1.43
    siehe
    1.43
     ">
    1.41
    </sup>
    1.38
    cookieParser
    1.36
    ("")){
    1.34
    到来
    1.30
    fetchone
    1.30
    ).
    1.27
    Activations Density 0.056%

    No Known Activations