© 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. 10-GEMMASCOPE-RES-131K
    7. 59905
    Prev
    Next
    INDEX
    Explanations

    code structures and types

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

    The neuron fires on numeric literals (sequences of digits) appearing 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
     that
    -1.77
     multifaceted
    -1.71
    诸多
    -1.70
     by
    -1.69
     unrelenting
    -1.66
     blistering
    -1.64
     unparalleled
    -1.55
     покри
    -1.55
     tireless
    -1.55
    ности
    -1.54
    POSITIVE LOGITS
     is
    2.02
     have
    1.91
    creating
    1.79
    噚
    1.75
    They
    1.71
     และ
    1.66
     trám
    1.66
     overly
    1.65
     Новости
    1.65
    
    1.64
    Activations Density 0.005%

    No Known Activations