© 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. 66285
    Prev
    Next
    INDEX
    Explanations

    God's or religious fulfillment

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

    This neuron strongly activates on common function words (especially short prepositions and articles like “in,” “a,” “the,” “del,” “un,” 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
    یرات
    -0.89
     arbete
    -0.87
    Manfaat
    -0.84
    mucha
    -0.81
    ழி
    -0.81
    acakt
    -0.80
    ınca
    -0.80
     rêves
    -0.79
     생각
    -0.76
     snabb
    -0.76
    POSITIVE LOGITS
     graced
    1.03
    namn
    0.98
     revealed
    0.96
     mysteriously
    0.95
    kfree
    0.92
     Logos
    0.91
     opened
    0.90
     છે
    0.90
     vocation
    0.90
    ğan
    0.89
    Activations Density 0.013%

    No Known Activations