© 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. 116581
    Prev
    Next
    INDEX
    Explanations

    words starting with gl

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

    This neuron fires on uppercase code tokens—particularly “GL”/GLSL and related shader‐language identifiers.

    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
    
    -0.83
    subscription
    -0.80
     assisti
    -0.78
    akhir
    -0.76
     充電
    -0.73
    でもない
    -0.71
     classica
    -0.71
    なんとか
    -0.71
    ៅ
    -0.71
    ⠘
    -0.71
    POSITIVE LOGITS
     Gl
    1.08
     gl
    0.86
    Gl
    0.84
     pay
    0.82
     GL
    0.81
    gl
    0.81
    Gle
    0.79
     Poppy
    0.79
     гло
    0.78
     deletions
    0.77
    Activations Density 0.062%

    No Known Activations