© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10566
    Prev
    Next
    INDEX
    Explanations

    Kingdoms and parables

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

    This neuron primarily detects explicit biblical references, such as names of biblical figures, scripture passages, and verse citations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ጼ
    0.56
     Godfrey
    0.55
     Aires
    0.53
     ionization
    0.52
    Letters
    0.51
     Clarendon
    0.51
    Potion
    0.51
     LETTERS
    0.50
     نامه
    0.49
    킵
    0.49
    POSITIVE LOGITS
     Kingdom
    0.83
     parable
    0.82
    kingdom
    0.79
     kingdom
    0.78
    Kingdom
    0.77
     Pharisees
    0.76
     Jesús
    0.74
     Galilee
    0.73
     discíp
    0.70
    Jesus
    0.68
    Activations Density 0.176%

    No Known Activations