© 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. 113872
    Prev
    Next
    INDEX
    Explanations

    words starting with co

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

    This neuron activates on the standalone token “Co” (as a capital-C, lower-o sequence), identifying occurrences of “Co” in names and abbreviations.

    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
    lossians
    -3.50
    leggio
    -2.94
    zembro
    -2.94
    sibirsk
    -2.92
    mining
    -2.67
    pertino
    -2.58
     科技
    -2.52
    that
    -2.48
     burch
    -2.41
    C
    -2.41
    POSITIVE LOGITS
     {
    2.81
     eventuell
    2.72
     &
    2.70
    ing
    2.67
     médaille
    2.59
    0
    2.52
    いえば
    2.48
     payé
    2.34
     was
    2.33
     Regarding
    2.25
    Activations Density 0.007%

    No Known Activations