© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75499
    Prev
    Next
    INDEX
    Explanations

    civic engagement and duty

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

    This neuron fires on the word “civic” (and its capitalized form) wherever it appears.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     slechts
    -0.92
    käse
    -0.91
     trabajan
    -0.90
    RDONLY
    -0.90
     apsau
    -0.87
    endencia
    -0.84
     nobis
    -0.83
    gdala
    -0.83
    彐
    -0.81
     Zeitpunkt
    -0.80
    POSITIVE LOGITS
     civic
    1.98
    civic
    1.73
     Civic
    1.59
    Civic
    1.57
     engagement
    1.35
     cív
    1.33
     Engagement
    1.23
     civ
    1.17
     minded
    1.13
    Engagement
    1.09
    Activations Density 0.012%

    No Known Activations