© 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. 98659
    Prev
    Next
    INDEX
    Explanations

    numbers and counts

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

    This neuron activates on numeric and quantity expressions (digits, number words, counts, and related tokens).

    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
     コード
    -0.78
    第
    -0.75
     もう
    -0.74
    วน
    -0.71
     verschiedenen
    -0.71
     kiedyś
    -0.71
     bijna
    -0.70
    Several
    -0.69
     Several
    -0.69
     jednego
    -0.68
    POSITIVE LOGITS
     six
    2.95
     seven
    2.92
     eight
    2.92
     five
    2.91
     nine
    2.64
     four
    2.64
     three
    2.14
     twelve
    2.06
    eight
    2.00
     eleven
    1.94
    Activations Density 0.162%

    No Known Activations