© 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. 63803
    Prev
    Next
    INDEX
    Explanations

    references to God

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     SERIAL
    -0.79
    XmlEnum
    -0.78
     TEMPERATURE
    -0.75
     nahilalakip
    -0.74
     PASSWORD
    -0.73
    cti
    -0.71
     thermodynamic
    -0.71
    utations
    -0.71
     Utilities
    -0.71
    metadata
    -0.71
    POSITIVE LOGITS
     God
    6.88
    God
    5.41
     GOD
    4.28
     god
    3.80
     Allah
    3.53
    GOD
    3.47
     Dieu
    3.14
     Dios
    3.14
    god
    3.13
     Бог
    3.00
    Activations Density 0.141%

    No Known Activations