© 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. 34-GEMMASCOPE-RES-131K
    4. 87051
    Prev
    Next
    INDEX
    Explanations

    XAML control tokens

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

    The neuron is selectively activated by numeric tokens (digit sequences in code, versions, years, percentages, etc.).

    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
     Covers
    -0.83
     coverings
    -0.77
    Covers
    -0.77
     covers
    -0.69
     System
    -0.68
     sys
    -0.67
     fumar
    -0.66
     system
    -0.66
    めている
    -0.66
    ชั่น
    -0.65
    POSITIVE LOGITS
    suke
    0.71
    Ming
    0.69
     McE
    0.68
    toarele
    0.66
    therape
    0.66
    inians
    0.65
    Prince
    0.65
    
    0.64
     Przed
    0.64
     brasileira
    0.63
    Activations Density 0.047%

    No Known Activations