© 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. 48020
    Prev
    Next
    INDEX
    Explanations

    sequential numbering and ordering

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

    The neuron activates strongly on mentions of “number” (and its variants like numbering, numbered) and related contexts about assigning or sequencing numbers.

    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
    ppelt
    -0.89
    呦
    -0.79
    ்த்த
    -0.77
    uklu
    -0.72
    estacks
    -0.72
     مقدار
    -0.71
    🈹
    -0.71
    ppin
    -0.71
    karakter
    -0.71
    ഒ
    -0.70
    POSITIVE LOGITS
     numbering
    3.72
     numbered
    3.72
     sequential
    3.09
    numbered
    3.09
     numbers
    2.59
    sequential
    2.52
    Sequential
    2.47
     Sequential
    2.45
     sequentially
    2.41
     numerical
    2.31
    Activations Density 0.173%

    No Known Activations