© 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. 79722
    Prev
    Next
    INDEX
    Explanations

    c++ includes

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

    The neuron fires strongly on the names of header files inside C/C++ #include directives.

    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
     verdaderamente
    -1.11
     realmente
    -1.09
    weihnachts
    -1.09
     sudad
    -1.08
     visibilidad
    -1.07
    쨩
    -1.07
     belangrijk
    -1.05
     capucha
    -1.05
    ίδι
    -1.05
     reseña
    -1.03
    POSITIVE LOGITS
     
    1.25
    ều
    1.01
     of
    0.97
    atów
    0.94
    uxley
    0.91
     ,
    0.90
    mmate
    0.90
    .
    0.89
     although
    0.87
     impulsive
    0.87
    Activations Density 0.005%

    No Known Activations