© 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. 10-GEMMASCOPE-RES-131K
    7. 87064
    Prev
    Next
    INDEX
    Explanations

    New Testament or Old Testament laws

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

    The neuron fires on mentions of major Biblical divisions—e.g. “Old Testament,” “New Testament,” “OT/NT,” “Old/New Covenant.”

    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
    0
    -1.64
    ⩕
    -1.63
    ſche
    -1.63
    蘩
    -1.61
    簠
    -1.59
    нутрен
    -1.59
    一颗
    -1.56
    られます
    -1.56
    もあるので
    -1.55
    藹
    -1.55
    POSITIVE LOGITS
    .)
    1.77
    不可能
    1.70
     aquellas
    1.69
    c
    1.61
    ?),
    1.60
    Once
    1.56
    ra
    1.53
    You
    1.52
    尤其是
    1.50
    ↵
    1.49
    Activations Density 0.004%

    No Known Activations