© 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. 32999
    Prev
    Next
    INDEX
    Explanations

    biblical verses and citations

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

    The neuron is selectively activating on the numeric tokens that serve as chapter and verse references in scripture citations.

    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
    O
    -1.34
    ことが
    -1.22
    ##
    -1.18
    ‐
    -1.13
    \_
    -1.13
    UN
    -1.13
    おわりに
    -1.12
    },
    -1.12
    P
    -1.11
    is
    -1.10
    POSITIVE LOGITS
    6
    1.63
    5
    1.59
    2
    1.58
    1
    1.43
    7
    1.39
    3
    1.34
     norvég
    1.33
     volantes
    1.32
     chrétien
    1.26
    嬉しいです
    1.24
    Activations Density 0.004%

    No Known Activations