© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 12106
    Prev
    Next
    INDEX
    Explanations

    religious servants and followers

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

    The neuron selectively fires on religious and theological terms (e.g. “Sister,” “Daughters,” “saved,” “grace,” “God,” “Satan”).

    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
    נחנו
    -0.77
     श्रे
    -0.73
    Felic
    -0.73
    是怎么
    -0.71
     proporcionan
    -0.71
     godfather
    -0.70
    老闆
    -0.68
    ớp
    -0.67
    tetur
    -0.67
    こちらが
    -0.66
    POSITIVE LOGITS
     servant
    3.08
     servants
    3.06
    servant
    1.98
     Servants
    1.95
     Servant
    1.94
    Serv
    1.93
    serv
    1.84
     agents
    1.73
    SERV
    1.73
     agent
    1.64
    Activations Density 0.032%

    No Known Activations