© 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. 10-GEMMASCOPE-RES-131K
    7. 101150
    Prev
    Next
    INDEX
    Explanations

    religious leaders and titles

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

    This neuron fires on named religious figures, titles, and related terms (e.g. “Imam,” “Rabbi,” “Pope,” saints’ names, confession, faith).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ﯼ
    -1.57
    鲀
    -1.49
     dérou
    -1.48
    komt
    -1.45
    plaatsen
    -1.45
     jeszcze
    -1.41
    ngulo
    -1.36
     helpen
    -1.33
     shrugs
    -1.32
    følge
    -1.30
    POSITIVE LOGITS
     they
    1.36
     vedea
    1.33
     навіть
    1.28
     infinita
    1.14
     elders
    1.13
    蛧
    1.12
    even
    1.11
     even
    1.11
     Даже
    1.11
     may
    1.10
    Activations Density 0.018%

    No Known Activations