© 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. 81428
    Prev
    Next
    INDEX
    Explanations

    numbers and arithmetic

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

    The neuron fires on individual digit tokens that are part of numerical sequences (long 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
     considerados
    -1.03
     една
    -0.98
    だったが
    -0.92
    貳
    -0.91
     işi
    -0.90
    hető
    -0.90
     compuestos
    -0.88
     abstrato
    -0.87
     acht
    -0.86
     betreffende
    -0.85
    POSITIVE LOGITS
    說道
    1.04
     actually
    1.02
    fileprivate
    0.97
    .`
    0.93
    จริงๆ
    0.92
     eigentlichen
    0.92
    uminio
    0.90
     esfuerzan
    0.90
    .?
    0.90
     kematian
    0.90
    Activations Density 0.068%

    No Known Activations