© 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. 73685
    Prev
    Next
    INDEX
    Explanations

    seats and ascension

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

    The neuron fires strongly on biblical scripture citations, especially book names followed by chapter and verse numbers.

    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
    娑
    -0.83
     schwarzen
    -0.83
    ண்டும்
    -0.81
    起床
    -0.81
     dlou
    -0.77
     Park
    -0.77
    王府
    -0.75
     Potential
    -0.75
     Enterprise
    -0.73
    setLoading
    -0.73
    POSITIVE LOGITS
     seat
    1.20
     Ascension
    1.16
     seating
    1.16
     seats
    1.15
     seated
    1.13
     ascended
    1.12
     ascension
    1.11
     sitting
    1.10
    Seat
    1.06
     Seats
    1.05
    Activations Density 0.012%

    No Known Activations