© 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. 34-GEMMASCOPE-RES-131K
    7. 45448
    Prev
    Next
    INDEX
    Explanations

    religious and academic topics

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

    The neuron flags mentions of biblical Scriptures—especially references to the Old Testament, its books, and related theological terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     pama
    -1.03
     Sout
    -0.98
     Arxiv
    -0.96
    ⚫
    -0.95
     tromper
    -0.94
     tuc
    -0.94
     FAL
    -0.93
    🫤
    -0.92
     marta
    -0.91
     poffible
    -0.91
    POSITIVE LOGITS
     (=
    1.00
    ıldız
    0.97
     motif
    0.95
    Israel
    0.95
    Yah
    0.95
     OT
    0.92
     Wisdom
    0.92
     ל
    0.92
     envision
    0.92
    ב
    0.90
    Activations Density 0.018%

    No Known Activations