© 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. 34-GEMMASCOPE-RES-131K
    7. 118903
    Prev
    Next
    INDEX
    Explanations

    Legislative Assembly, riding, election

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

    The neuron strongly activates on tokens describing a person’s formal political office or membership (e.g. “was,” “member,” “Legislative Assembly,” party names, dates), i.e. statements of holding or representing elected positions.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ਜ਼
    -0.73
     streaming
    -0.72
    Prensa
    -0.72
     washers
    -0.71
    Philosophy
    -0.71
     privilégi
    -0.71
    Philosop
    -0.66
     queue
    -0.66
    |=\
    -0.66
    捅
    -0.66
    POSITIVE LOGITS
     Hon
    0.82
     resumes
    0.78
     reclamation
    0.76
    hinged
    0.76
     honoring
    0.76
    Compiled
    0.75
     יְ
    0.74
     restoration
    0.74
     بم
    0.73
    Payer
    0.73
    Activations Density 0.018%

    No Known Activations