© 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. 55937
    Prev
    Next
    INDEX
    Explanations

    Church of Jesus Christ

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

    The neuron flags multi‐word proper‐noun strings that name formal organizations or institutions (e.g. “Church of Jesus Christ of Latter-day Saints,” “County Court at Law,” “Buy Me A Coffee”).

    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
     khỏe
    -0.68
     frequently
    -0.66
    鐸
    -0.66
     Membran
    -0.66
     Adri
    -0.65
     Arya
    -0.65
    indir
    -0.65
     overcame
    -0.63
     wipes
    -0.63
     thoroughly
    -0.63
    POSITIVE LOGITS
     offensive
    0.69
    letic
    0.69
    cheria
    0.68
     Clapton
    0.68
     福
    0.68
    رده
    0.67
    remont
    0.66
    徨
    0.66
     EClass
    0.65
     rincón
    0.65
    Activations Density 0.091%

    No Known Activations