© 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. 45532
    Prev
    Next
    INDEX
    Explanations

    royal titles and leaders

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

    The neuron strongly activates on the structural labels and key field names found in a Wikipedia-style infobox (e.g. “Incumbents,” “Emir,” “Prime Minister,” dates, event headings).

    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
    .."
    -1.41
     ライト
    -1.41
    ޭ
    -1.38
     embellished
    -1.35
     THRO
    -1.34
    龗
    -1.32
     USAID
    -1.30
    iens
    -1.30
     affront
    -1.30
    삵
    -1.23
    POSITIVE LOGITS
     their
    1.85
     could
    1.59
     what
    1.46
     it
    1.42
     there
    1.34
     political
    1.30
     has
    1.30
     had
    1.27
     give
    1.27
     might
    1.25
    Activations Density 0.049%

    No Known Activations