© 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. 10-GEMMASCOPE-RES-131K
    7. 113099
    Prev
    Next
    INDEX
    Explanations

    religious and proper nouns

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

    The neuron detects mentions of core Christian religious terms—especially names like God, Jesus, and 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_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
     like
    -1.66
     in
    -1.60
     to
    -1.49
     too
    -1.45
    oxia
    -1.34
     while
    -1.31
    不上
    -1.30
    vertebrates
    -1.30
    butuhkan
    -1.25
     not
    -1.24
    POSITIVE LOGITS
     PUSTAKA
    1.57
    wego
    1.47
     gustó
    1.41
    sitivity
    1.38
     scrittore
    1.36
     Zwiebel
    1.32
     régiment
    1.29
    ẾT
    1.27
     Irland
    1.27
    攷
    1.23
    Activations Density 0.012%

    No Known Activations