© 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. 78429
    Prev
    Next
    INDEX
    Explanations

    god, lord, christ, allah

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

    The neuron activates on words referring to the divine—names or titles of God (e.g. Lord, God, Jesus, Holy Spirit, Allah, Christ).

    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
     or
    -1.19
     After
    -0.98
    After
    -0.95
     If
    -0.93
    When
    -0.93
     sleek
    -0.92
    際は
    -0.91
    排行
    -0.90
     немного
    -0.90
    様の
    -0.90
    POSITIVE LOGITS
     who
    1.86
     whom
    1.59
     himself
    1.54
    whom
    1.43
     Himself
    1.34
     Almighty
    1.33
    himself
    1.21
    whose
    1.20
     almighty
    1.14
    Creator
    1.09
    Activations Density 0.024%

    No Known Activations