© 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. 10-GEMMASCOPE-RES-131K
    4. 124653
    Prev
    Next
    INDEX
    Explanations

    offering sacrifice worship gift

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

    The neuron detects references to religious rituals and ceremonial offerings (e.g., “offering,” “Eucharistic,” “Mass,” “sacrifice,” “worship”).

    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
    For
    -1.64
    if
    -1.64
    in
    -1.61
    To
    -1.59
    In
    -1.54
    No
    -1.52
     if
    -1.50
    Do
    -1.39
    On
    -1.37
    If
    -1.34
    POSITIVE LOGITS
    amerikanischer
    1.45
     distinguer
    1.44
    飧
    1.42
    ronesia
    1.39
    攰
    1.38
     มัน
    1.37
    铪
    1.35
    enfone
    1.34
     déterminer
    1.34
    unicaciones
    1.34
    Activations Density 0.022%

    No Known Activations