© 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. 11566
    Prev
    Next
    INDEX
    Explanations

    connecting words and lists

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

    The neuron activates on numeric values—especially decimal numbers and quantitative measurements—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
    Also
    -2.03
    In
    -2.02
    To
    -2.00
    Although
    -1.95
    Setelah
    -1.95
    For
    -1.93
     даже
    -1.89
    {
    
    -1.88
    After
    -1.88
    Meskipun
    -1.78
    POSITIVE LOGITS
    奩
    1.92
    婠
    1.84
     to
    1.84
    っております
    1.83
     město
    1.77
     великолеп
    1.70
     отличаются
    1.69
    文分享
    1.69
     such
    1.64
     into
    1.59
    Activations Density 0.229%

    No Known Activations