© 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. 22-GEMMASCOPE-RES-131K
    7. 84075
    Prev
    Next
    INDEX
    Explanations

    function calls and code blocks

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

    This neuron detects numeric literals or standalone numbers in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     integriert
    -1.00
     wegen
    -0.91
    
    -0.90
     dauern
    -0.88
    
    -0.88
     礼物
    -0.85
     شيئ
    -0.84
     ravages
    -0.83
    
    -0.83
    mtb
    -0.83
    POSITIVE LOGITS
     if
    1.60
     that
    1.59
     it
    1.11
     conseguido
    1.07
     or
    1.00
     its
    0.95
     ако
    0.93
     mochilas
    0.93
     如果
    0.91
    hava
    0.90
    Activations Density 0.009%

    No Known Activations