© 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. 10-GEMMASCOPE-RES-131K
    7. 84969
    Prev
    Next
    INDEX
    Explanations

    Category / Description / Guinea / Brunei / Capoeira / rugby / Help

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

    The neuron is triggered by structural labels and metadata tokens—things like section headings, navigation labels, category names, and other document‐outline markers.

    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
     for
    -2.45
     as
    -1.70
     which
    -1.55
     or
    -1.55
     because
    -1.52
     if
    -1.48
     now
    -1.45
    apj
    -1.44
     from
    -1.41
    瑚
    -1.36
    POSITIVE LOGITS
    hline
    1.62
    many
    1.54
    more
    1.52
     signific
    1.51
    way
    1.48
    ─
    1.45
    をご覧ください
    1.43
    R
    1.39
    MORE
    1.38
     provoc
    1.38
    Activations Density 0.062%

    No Known Activations