© 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. 98887
    Prev
    Next
    INDEX
    Explanations

    blessed by

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

    The neuron fires on devotional honorifics and praise adjectives (e.g. “blessed,” “gracious,” “sweet”) commonly found in prayers.

    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
    ledo
    -0.77
    cheduled
    -0.72
     fuera
    -0.72
     kam
    -0.68
    maak
    -0.68
    בוק
    -0.67
     variaciones
    -0.67
    ress
    -0.67
     Vele
    -0.67
    PREC
    -0.66
    POSITIVE LOGITS
    収入
    0.73
     conquerors
    0.68
    Cro
    0.65
     sideboard
    0.63
     blackboard
    0.63
     commutative
    0.62
    ṟ
    0.62
    Difference
    0.61
    THM
    0.61
    Tro
    0.60
    Activations Density 0.069%

    No Known Activations