© 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. 90260
    Prev
    Next
    INDEX
    Explanations

    spiritual leaders and masters

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

    The neuron specifically fires on capitalized honorifics or titles in religious and spiritual names (e.g. “Guru,” “Dr,” “Shaykh,” “Sadghuru,” “Shree,” etc.).

    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
    цет
    -0.76
    antina
    -0.76
    NTA
    -0.74
    пишите
    -0.73
     Christian
    -0.73
     terenie
    -0.72
     опор
    -0.71
    чка
    -0.69
    iq
    -0.69
     baptism
    -0.69
    POSITIVE LOGITS
     Master
    1.34
     teacher
    1.29
     master
    1.23
    Master
    1.22
     MASTER
    1.21
     mestre
    1.18
    MASTER
    1.14
     Teacher
    1.13
     استاد
    1.07
     הרב
    1.07
    Activations Density 0.038%

    No Known Activations