© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 103690
    Prev
    Next
    INDEX
    Explanations

    religious names and titles

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

    The neuron detects mentions of specific Christian religious figures, saints, or feast/event names.

    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
     pourraient
    -1.54
    ܊
    -1.47
    indelijk
    -1.47
     kopen
    -1.42
     ningún
    -1.41
     welches
    -1.39
     pesso
    -1.38
     captiv
    -1.37
     acheter
    -1.34
     onbe
    -1.34
    POSITIVE LOGITS
     of
    1.89
     at
    1.76
     by
    1.64
     all
    1.48
     I
    1.32
     with
    1.24
    All
    1.24
     не
    1.23
    with
    1.17
     without
    1.16
    Activations Density 0.033%

    No Known Activations