© 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. 65606
    Prev
    Next
    INDEX
    Explanations

    South West England

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

    The neuron consistently activates on digit sequences (numbers) in the 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_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
    实
    -0.75
     neuro
    -0.73
     GC
    -0.69
     intervenciones
    -0.69
     Nav
    -0.69
     Nissan
    -0.69
     Neuro
    -0.68
    ча
    -0.68
    Hal
    -0.68
     Hampton
    -0.67
    POSITIVE LOGITS
     Somerset
    1.50
     Glastonbury
    1.39
    Somer
    1.28
     Cheddar
    0.98
     Taunton
    0.84
     Bristol
    0.78
    もしれません
    0.77
     cheddar
    0.76
     tamp
    0.74
     запла
    0.74
    Activations Density 0.009%

    No Known Activations