© 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. 22-GEMMASCOPE-RES-131K
    7. 130823
    Prev
    Next
    INDEX
    Explanations

    The neuron specializes in spotting numeric citation tokens—especially numbers and decimal-formatted volume, issue, or page references.

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

    citations and references

    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
    нгредіє
    -0.88
    Скачать
    -0.86
    問題は
    -0.85
     {
    -0.85
    рация
    -0.82
    chées
    -0.82
     свър
    -0.81
     as
    -0.79
     LEAVE
    -0.79
    uevos
    -0.78
    POSITIVE LOGITS
     Canning
    0.95
     într
    0.88
    archiviato
    0.86
     amine
    0.84
     śnie
    0.83
     verschillende
    0.82
    いよいよ
    0.82
     لمس
    0.81
     Flexibility
    0.79
     australian
    0.79
    Activations Density 0.001%

    No Known Activations