© 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. 64524
    Prev
    Next
    INDEX
    Explanations

    consisting of parts

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

    The neuron flags low‐frequency or domain-specific tokens—proper names, technical jargon, numbers, and other uncommon words.

    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
    泞
    -0.88
    xid
    -0.86
     неболь
    -0.80
     this
    -0.79
    ensões
    -0.73
    ěr
    -0.73
    Ꭿ
    -0.73
    (!
    -0.73
    apis
    -0.72
    例文
    -0.72
    POSITIVE LOGITS
     series
    1.68
     consisting
    1.49
    series
    1.39
     comprised
    1.22
    Series
    1.20
     consists
    1.20
     consisted
    1.20
    ชุด
    1.17
     група
    1.15
     cluster
    1.14
    Activations Density 0.232%

    No Known Activations