© 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. 70079
    Prev
    Next
    INDEX
    Explanations

    secularism and atheism

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

    The neuron activates on ideological or religious labels—especially words ending in “-ism” (e.g. secularism, Islamism) or names of religions like Islam.

    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
     būt
    -0.77
    مزید
    -0.75
    preset
    -0.75
    🐒
    -0.75
    mex
    -0.74
     conservatives
    -0.74
    倢
    -0.74
    Validator
    -0.73
    asis
    -0.72
    Iframe
    -0.72
    POSITIVE LOGITS
     secular
    5.09
     Secular
    3.86
    sec
    2.11
     секу
    1.95
     atheist
    1.84
     atheists
    1.82
     Athe
    1.59
     SEC
    1.51
    Sec
    1.51
     العلم
    1.45
    Activations Density 0.050%

    No Known Activations