© 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. 112341
    Prev
    Next
    INDEX
    Explanations

    spirituality and spiritual life

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

    The neuron fires on words related to spiritual or religious concepts and contexts.

    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
     votación
    -1.55
     cuyas
    -1.53
     cuyos
    -1.50
    >
    -1.49
     supuestamente
    -1.48
     mehreren
    -1.47
     mehrere
    -1.47
    )-
    -1.40
     تھا
    -1.39
    口水
    -1.38
    POSITIVE LOGITS
    this
    1.59
     yaka
    1.47
     tortuga
    1.41
     bypassing
    1.37
     otel
    1.35
     drau
    1.34
     abstracta
    1.34
    蕯
    1.33
    tividade
    1.33
     blanca
    1.32
    Activations Density 0.018%

    No Known Activations