© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38269
    Prev
    Next
    INDEX
    Explanations

    sentence boundaries

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

    This neuron fires on non-prose “section marker” tokens—things like headings, titles, call-to-action exclamations, code labels, or other fragmentary labels rather than running-sentence text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    jęcia
    -1.14
     ícone
    -1.07
     prêmio
    -1.01
     wholly
    -0.99
     navíc
    -0.99
     dianteiro
    -0.98
     svå
    -0.97
     hitherto
    -0.96
    かります
    -0.96
    鐺
    -0.96
    POSITIVE LOGITS
    Toponymie
    1.01
    Tra
    0.99
    ines
    0.93
     Operational
    0.93
     основ
    0.93
    its
    0.92
     разные
    0.88
     основные
    0.87
    ras
    0.87
    ik
    0.87
    Activations Density 0.002%

    No Known Activations