© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107302
    Prev
    Next
    INDEX
    Explanations

    helping the community

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

    This neuron fires on explicitly Christian or church-themed doctrinal language—phrases about God’s Spirit, Christian ethics (love, care, embodying, incarnation, Jesus’ footsteps), and similar theological expressions.

    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
     deportivo
    -0.98
    editary
    -0.96
     Pantalla
    -0.85
     éclair
    -0.83
    ślę
    -0.82
    astify
    -0.82
     homeschool
    -0.81
    aspx
    -0.78
    internet
    -0.78
     DEVICE
    -0.77
    POSITIVE LOGITS
     caring
    1.20
     neighbor
    1.05
     serving
    1.03
     neighbour
    1.02
     social
    1.02
     service
    1.01
     love
    1.00
    caring
    1.00
     compassion
    0.99
     care
    0.97
    Activations Density 0.027%

    No Known Activations