© 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. 71514
    Prev
    Next
    INDEX
    Explanations

    bible book names

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

    The neuron strongly fires on Bible verse citations and other parenthesized scripture references (book names, chapter : verse numbers, and quotation delimiters).

    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
     its
    -1.20
     kolam
    -0.98
    Its
    -0.96
    It
    -0.95
    ≈
    -0.92
     pubblicato
    -0.91
    ねる
    -0.91
    continence
    -0.91
    any
    -0.91
    its
    -0.91
    POSITIVE LOGITS
     сахара
    1.16
    edakan
    1.09
    ֩
    1.07
     montrant
    1.01
     peintre
    0.99
     जाएगा
    0.99
    weetie
    0.98
    Arti
    0.97
     mérit
    0.96
     rencontr
    0.96
    Activations Density 0.004%

    No Known Activations