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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2870
    Prev
    Next
    INDEX
    Explanations

    god acts towards others

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

    The neuron fires on phrases describing Christian religious language or theology—e.g. attributes of God, the church, or God’s love and work.

    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
     God
    -2.05
    God
    -1.61
     Allah
    -1.51
     GOD
    -1.48
     Dieu
    -1.31
    上帝
    -1.27
     خداوند
    -1.16
     Бог
    -1.16
     Dios
    -1.12
    GOD
    -1.09
    POSITIVE LOGITS
     his
    1.91
     His
    1.38
     Himself
    1.36
    His
    1.35
     Seu
    1.14
     himself
    1.09
     HIS
    1.05
     humans
    1.05
     you
    1.00
     Zijn
    0.95
    Activations Density 0.029%

    No Known Activations