© 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. 29895
    Prev
    Next
    INDEX
    Explanations

    titles and introductory phrases after colons or specific symbols

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

    The neuron fires on devotional or gratitude statements addressed to God (e.g. “I pray to God…,” “We thank God for…”).

    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
    рин
    -0.82
    ຽ
    -0.79
     iniciado
    -0.78
     ditulis
    -0.77
    amilya
    -0.75
     incorporado
    -0.74
     dihasilkan
    -0.74
     voeren
    -0.73
    armi
    -0.71
     elaborado
    -0.71
    POSITIVE LOGITS
    edero
    0.77
     Toibin
    0.77
     vano
    0.77
    ſu
    0.77
    typename
    0.76
    ACE
    0.75
     Alcott
    0.75
     bilo
    0.75
    ıyı
    0.75
    IFIED
    0.73
    Activations Density 0.004%

    No Known Activations