© 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. 62538
    Prev
    Next
    INDEX
    Explanations

    government departments and roles

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

    This neuron detects mentions of government bodies, political parties, official offices, and titles (e.g., “Department for Transport,” “Conservative Party,” “Member of Parliament”).

    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
     grin
    -0.88
    Dirk
    -0.79
    Grund
    -0.75
     kimse
    -0.75
    grocery
    -0.71
    OHN
    -0.71
     arşiv
    -0.69
    ZING
    -0.69
    ASHINGTON
    -0.69
     kolay
    -0.68
    POSITIVE LOGITS
     environment
    0.89
     transport
    0.82
     Children
    0.81
     Yard
    0.79
     Environment
    0.79
    Environment
    0.78
     Secretary
    0.78
     employment
    0.77
     дети
    0.77
    Secretary
    0.74
    Activations Density 0.035%

    No Known Activations