© 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. 107740
    Prev
    Next
    INDEX
    Explanations

    numbers and labels

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

    The neuron strongly activates on numeric tokens (years, dates, counts, or standalone digits).

    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
     Leven
    -0.81
    ById
    -0.79
     мебель
    -0.75
    Chancellor
    -0.75
     kh
    -0.75
    nbar
    -0.72
     Flames
    -0.71
    нце
    -0.71
    Lloyd
    -0.71
     иници
    -0.70
    POSITIVE LOGITS
    Continuar
    0.94
     continuing
    0.94
     continuare
    0.93
     inherently
    0.78
     shouted
    0.78
    Kosten
    0.78
    isGrid
    0.77
    carrinho
    0.77
     Gehir
    0.76
    Tienda
    0.75
    Activations Density 0.002%

    No Known Activations