© 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. 22-GEMMASCOPE-RES-131K
    7. 75049
    Prev
    Next
    INDEX
    Explanations

    bishop of a place

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

    The neuron fires strongly on words denoting high-ranking Catholic or Anglican church offices and titles (e.g. Bishop, Archbishop, Cardinal, prelate).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    だけに
    -2.13
     pomoci
    -2.06
    を始め
    -2.03
    艄
    -1.95
    沨
    -1.95
     ließen
    -1.94
     ใน
    -1.91
    ,"
    -1.90
    の方に
    -1.89
    —"
    -1.88
    POSITIVE LOGITS
    ６
    2.11
    𖥧
    2.05
    </h1>
    2.00
    geſ
    1.98
    3
    1.91
    ⦊
    1.89
     When
    1.81
     amerikan
    1.81
    首先
    1.80
    On
    1.79
    Activations Density 0.015%

    No Known Activations