© 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. 34-GEMMASCOPE-RES-131K
    7. 49233
    Prev
    Next
    INDEX
    Explanations

    psalm or enemies

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

    This neuron specifically detects lines of numbered Biblical scripture verses (e.g., Psalm passages with verse numbers).

    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
     Yesus
    -0.86
     Pflicht
    -0.81
     rallado
    -0.81
    AppContext
    -0.77
    視聴
    -0.73
    fael
    -0.73
     toki
    -0.73
    lds
    -0.72
    glas
    -0.72
     obowią
    -0.72
    POSITIVE LOGITS
     Psalm
    1.30
     psalm
    1.17
     Enemies
    1.17
    Psalm
    1.16
     psal
    1.12
     Psal
    1.11
     PSL
    1.10
    Enemies
    1.09
     Psalms
    1.09
     enemies
    1.00
    Activations Density 0.011%

    No Known Activations