© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16360
    Prev
    Next
    INDEX
    Explanations

    biblical names and numbers

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

    The neuron activates on numbered citation-like sequences—particularly chapter:verse or section references (e.g. “Mark 3:6”, “John 3:16”, “Ex 3:1”).

    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
     would
    -1.34
     monumento
    -1.12
     białym
    -1.09
    CHEZ
    -1.03
     all
    -1.00
     amongst
    -1.00
     could
    -0.94
     had
    -0.94
    !!!!
    -0.92
     Anderson
    -0.91
    POSITIVE LOGITS
    ussia
    1.17
     "]";
    1.16
     Obtén
    1.15
     mediante
    1.15
    </h4>
    1.08
    豋
    1.08
    在这
    1.07
    ritation
    1.07
     WENT
    1.07
    この記事
    1.05
    Activations Density 0.000%

    No Known Activations