© 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. 34-GEMMASCOPE-RES-131K
    7. 98300
    Prev
    Next
    INDEX
    Explanations

    twig, macro, extends, controller

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

    The neuron strongly activates on template‐language delimiters (e.g. Twig/Handlebars “{{”, “{%”, 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_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
     середи
    -0.80
    gorro
    -0.76
     apareció
    -0.75
    Systematic
    -0.75
    accepte
    -0.74
    patrón
    -0.74
     específicamente
    -0.74
     dessas
    -0.73
    DHA
    -0.73
     participó
    -0.73
    POSITIVE LOGITS
    macros
    0.91
     macros
    0.87
     Macros
    0.78
     macro
    0.78
    |
    0.77
     Macro
    0.76
     nomine
    0.74
    volt
    0.74
    macro
    0.74
     Teixeira
    0.71
    Activations Density 0.049%

    No Known Activations