© 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. 22-GEMMASCOPE-RES-131K
    4. 79957
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    This neuron detects standalone numeric tokens (e.g. volume, issue, page, year, DOI numbers) in citation or reference text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     which
    -1.79
     of
    -1.56
     should
    -1.28
     while
    -1.27
     would
    -1.25
     from
    -1.25
     could
    -1.24
     these
    -1.20
     when
    -1.19
     until
    -1.19
    POSITIVE LOGITS
    Seni
    1.38
    Evet
    1.38
    Doktor
    1.37
    Gön
    1.34
    Teknik
    1.34
    Aç
    1.28
    zdroj
    1.28
    Karakter
    1.27
    Cevap
    1.27
    Ilustra
    1.25
    Activations Density 0.001%

    No Known Activations