© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71918
    Prev
    Next
    INDEX
    Explanations

    addressing father or lord

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

    The neuron detects direct invocations or addresses to a deity (e.g. “Father,” “Lord,” “O Lord,” “God”) in a prayer or devotional context.

    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
     these
    -1.50
     other
    -1.08
     an
    -1.05
     this
    -1.04
     presenta
    -1.02
     pemilihan
    -0.98
    kori
    -0.98
    וּ
    -0.98
     perdiendo
    -0.98
    ',{
    -0.97
    POSITIVE LOGITS
     τὴν
    1.26
     τοῦ
    1.19
     grant
    1.19
     thank
    1.16
    thly
    1.10
     τὸν
    1.09
     softshell
    1.09
     מים
    1.09
    Dear
    1.07
     renforcé
    1.07
    Activations Density 0.005%

    No Known Activations