© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15043
    Prev
    Next
    INDEX
    Explanations

    links and markup

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

    The neuron is spotting reStructuredText markup markers, especially lines beginning with “..” and related RST punctuation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     from
    -2.09
     after
    -1.95
     at
    -1.80
     because
    -1.77
     when
    -1.77
     that
    -1.73
     unrelenting
    -1.72
     with
    -1.71
     of
    -1.71
     which
    -1.67
    POSITIVE LOGITS
    
    1.83
     .......
    1.77
     adesivo
    1.75
     cuatro
    1.70
     $^{\
    1.68
    擻
    1.66
     această
    1.66
     llavero
    1.65
     ícones
    1.64
     ..........
    1.62
    Activations Density 0.054%

    No Known Activations