© 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. 98462
    Prev
    Next
    INDEX
    Explanations

    recurring roles

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

    The neuron activates on numeric characters and their punctuation (digits, decimal points, and commas).

    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
    illaume
    -0.73
     VARIOUS
    -0.71
     vacancies
    -0.71
    udahan
    -0.70
     moderne
    -0.69
     gratuitamente
    -0.68
    內容簡介
    -0.67
     الدر
    -0.67
    斋
    -0.67
    ว่าง
    -0.66
    POSITIVE LOGITS
     recurring
    5.66
     recurrent
    4.59
    recurring
    4.53
    Recurring
    4.22
     Recur
    3.97
     recur
    3.34
     Recurrent
    3.33
     repeating
    3.25
     recurrence
    3.20
     repeated
    3.02
    Activations Density 0.107%

    No Known Activations