© 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. 98691
    Prev
    Next
    INDEX
    Explanations

    devotee

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

    The neuron strongly activates on mentions of Hindu deity names and titles (e.g. “Lord Narasimha,” incarnation references, related proper names).

    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
    cheque
    -0.79
    REVISTA
    -0.74
    liath
    -0.73
    的前
    -0.73
    revista
    -0.71
     胡
    -0.70
    tika
    -0.69
    Inp
    -0.69
    另外
    -0.68
    xelles
    -0.68
    POSITIVE LOGITS
     devotional
    1.39
     devotion
    1.35
     devoted
    1.10
     devotees
    1.07
     devotee
    1.05
     Devotion
    1.03
     devote
    1.00
    Devo
    0.95
    devo
    0.94
     Devo
    0.90
    Activations Density 0.022%

    No Known Activations