© 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. 2533
    Prev
    Next
    INDEX
    Explanations

    references to pages

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

    The main thing this neuron does is detect numeric tokens (such as citation numbers, page or section numbers, years, and other numerical references).

    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
    rei
    -0.82
     秋冬
    -0.77
     nettoy
    -0.73
    empat
    -0.73
    zelf
    -0.73
    午
    -0.72
     eure
    -0.71
     اول
    -0.70
    Decent
    -0.70
     vậy
    -0.70
    POSITIVE LOGITS
     page
    3.20
     on
    2.69
    page
    2.50
     Page
    2.20
    Page
    2.09
     página
    2.06
     pages
    1.92
     pg
    1.83
    PAGE
    1.62
    ページ
    1.54
    Activations Density 0.025%

    No Known Activations