© 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. 22-GEMMASCOPE-RES-131K
    7. 128210
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on standalone numeric tokens (integers or decimals) used for section numbers, page counts, enumerations, or other numeric labels.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    section identifiers and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     disebutkan
    -1.63
     Meksi
    -1.52
     konsep
    -1.46
    了什么
    -1.46
     églises
    -1.45
    取决
    -1.41
     metode
    -1.39
     chré
    -1.38
     menem
    -1.38
    ׇ
    -1.38
    POSITIVE LOGITS
     hierdie
    1.63
    )
    1.62
    亟
    1.55
    暧
    1.45
    וּ
    1.39
    づくり
    1.36
     \
    1.34
     $\
    1.32
    它
    1.28
     теря
    1.25
    Activations Density 0.520%

    No Known Activations