© 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. 11712
    Prev
    Next
    INDEX
    Explanations

    TCP network protocol

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

    The neuron specializes in spotting numeric tokens (sequences of digits) in technical protocol and specification contexts.

    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
    ))^{
    -1.34
    
    -1.33
    cześ
    -1.15
    CANADA
    -1.13
    ノコ
    -1.13
    
    -1.09
     eerder
    -1.09
    CLOUD
    -1.09
     here
    -1.07
     desenli
    -1.06
    POSITIVE LOGITS
     two
    1.25
     will
    1.23
     RoutedEventArgs
    1.20
    istia
    1.20
     veckan
    1.16
     AssemblyVersion
    1.13
     ['./
    1.13
     जब
    1.09
    ممنون
    1.07
    rália
    1.07
    Activations Density 0.079%

    No Known Activations