© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118238
    Prev
    Next
    INDEX
    Explanations

    holy spirit guidance

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

    The neuron activates on occurrences of the word “Spirit,” especially in the phrase “Holy Spirit.”

    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
    \">\
    -0.80
    papier
    -0.79
    有一些
    -0.79
     Invitational
    -0.77
     pigment
    -0.77
     organisiert
    -0.75
    meye
    -0.73
     Pigment
    -0.72
     Mock
    -0.71
    imper
    -0.71
    POSITIVE LOGITS
     Comfor
    1.07
     guide
    1.04
     comforter
    1.03
     convict
    0.92
     guides
    0.90
     помо
    0.85
     Guide
    0.81
     convencer
    0.81
     gifts
    0.81
     Counselor
    0.81
    Activations Density 0.003%

    No Known Activations