© 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. 130834
    Prev
    Next
    INDEX
    Explanations

    code, commands, configuration

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

    The neuron fires on programming‐style identifiers (library or API names, function calls, class/module names, 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_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
    此外
    -1.45
    {
    -1.37
     huset
    -1.37
     netts
    -1.34
    şil
    -1.30
    俣
    -1.27
     رون
    -1.27
    Confira
    -1.27
     estekak
    -1.27
     parfois
    -1.27
    POSITIVE LOGITS
    
    1.59
     that
    1.54
     червня
    1.48
     eficaz
    1.47
     if
    1.45
     or
    1.39
     when
    1.38
     quickly
    1.34
     dispozici
    1.34
     such
    1.33
    Activations Density 0.044%

    No Known Activations