© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105483
    Prev
    Next
    INDEX
    Explanations

    countries and regions

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

    The neuron primarily detects numerical expressions (digits, durations, percentages, prices) 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_10/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
     of
    -1.92
     
    -1.42
    毉
    -1.28
    OOTDTY
    -1.27
    曏
    -1.27
    就
    -1.25
    ⎘
    -1.24
    と呼ばれる
    -1.23
     queria
    -1.23
    Sábado
    -1.22
    POSITIVE LOGITS
     or
    2.33
     this
    2.23
    涑
    1.73
    ďte
    1.70
     твои
    1.61
    ってください
    1.59
     этом
    1.55
     your
    1.54
     ataupun
    1.52
    You
    1.48
    Activations Density 0.100%

    No Known Activations