© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40730
    Prev
    Next
    INDEX
    Explanations

    Lord and Savior

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

    The neuron detects mentions of core Christian theological entities and concepts (e.g. God, Jesus Christ, the Holy Spirit, Lord, Savior).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    -1.68
     эти
    -1.63
     estos
    -1.62
     этих
    -1.61
     negó
    -1.58
     also
    -1.56
    Väl
    -1.54
     programmet
    -1.54
    announced
    -1.52
    ..."
    -1.49
    POSITIVE LOGITS
     promove
    1.61
     comanda
    1.37
    詎
    1.33
    んでしょう
    1.32
     fiducia
    1.32
     gravidanza
    1.31
     depicted
    1.30
     farmaco
    1.30
     lancia
    1.29
     isolamento
    1.28
    Activations Density 0.047%

    No Known Activations