© 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. 99013
    Prev
    Next
    INDEX
    Explanations

    listing examples or items

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

    The neuron strongly activates on the words “include” or “including,” i.e. tokens that introduce a list or set of examples.

    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
     with
    -1.94
     for
    -1.90
     and
    -1.89
     on
    -1.80
     this
    -1.79
     in
    -1.73
     their
    -1.61
     does
    -1.59
     which
    -1.59
     where
    -1.53
    POSITIVE LOGITS
    厹
    1.60
    AFTER
    1.59
    {
    1.55
     skues
    1.54
    THEN
    1.53
    傒
    1.52
     Anſ
    1.52
     doivent
    1.48
     siku
    1.48
    깬
    1.46
    Activations Density 0.064%

    No Known Activations