© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 11786
    Prev
    Next
    INDEX
    Explanations

    denominational churches

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

    The neuron is strongly activated by occurrences of the phrase “Methodist Church,” effectively detecting mentions of that denomination.

    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
     católica
    -1.04
     catholic
    -1.00
    avits
    -0.86
    carril
    -0.84
    Catholic
    -0.84
    タウン
    -0.84
    ヨーグルト
    -0.83
     като
    -0.81
    catholic
    -0.81
     CATH
    -0.79
    POSITIVE LOGITS
     Church
    1.69
     church
    1.41
     churches
    1.30
     Churches
    1.12
    Church
    1.10
    church
    1.06
     Kirche
    1.00
    cová
    0.93
     CHURCH
    0.90
    ism
    0.85
    Activations Density 0.025%

    No Known Activations