© 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. 10-GEMMASCOPE-RES-131K
    7. 43194
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers

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

    This neuron fires on ordinal‐number suffixes (e.g. the “th” in “17th” or “19th”) that mark dates or positional labels.

    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
    </b>
    -2.33
    从来没有
    -2.20
                    
    -2.20
    諼
    -2.03
    medriver
    -1.94
    irchen
    -1.94
     vítimas
    -1.88
    寕
    -1.88
    今後も
    -1.87
     haven
    -1.86
    POSITIVE LOGITS
    .
    2.66
    ',
    2.34
    {
    2.11
    [
    2.08
    e
    1.95
    śmy
    1.95
    </h3>
    1.92
     Weird
    1.88
    )
    1.80
     titolata
    1.80
    Activations Density 0.058%

    No Known Activations