© 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. 58217
    Prev
    Next
    INDEX
    Explanations

    be followed by state

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

    the neuron detects occurrences of the verb “be.”

    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
     That
    -1.61
     tiresome
    -1.52
     This
    -1.50
    ing
    -1.48
     nifty
    -1.45
    вольно
    -1.41
     metamorphosis
    -1.40
    midrule
    -1.40
     Not
    -1.38
    家的
    -1.36
    POSITIVE LOGITS
    籥
    1.73
    盦
    1.73
     パネル
    1.54
     限定
    1.51
     ถ้า
    1.48
    WHY
    1.48
    賔
    1.48
    臜
    1.46
     大き
    1.42
    ED
    1.39
    Activations Density 0.021%

    No Known Activations