© 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. 34-GEMMASCOPE-RES-131K
    7. 118047
    Prev
    Next
    INDEX
    Explanations

    Q followed by Wilcox

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

    The neuron strongly activates on tokens composed of digits (e.g. years or numeric strings) and on apostrophe‐containing fragments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ición
    -0.78
    щено
    -0.73
    oat
    -0.72
    щото
    -0.71
     Malaysia
    -0.70
     Aiken
    -0.70
     Donetsk
    -0.69
     Communications
    -0.69
     Cinema
    -0.69
     Byrne
    -0.69
    POSITIVE LOGITS
     شدید
    0.83
     trang
    0.75
    prisma
    0.73
     prisma
    0.71
     کشاور
    0.71
    strze
    0.70
    ￣)
    0.69
     palms
    0.68
     Banca
    0.68
    RequestHandler
    0.66
    Activations Density 0.023%

    No Known Activations