© 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. 10-GEMMASCOPE-RES-131K
    7. 68903
    Prev
    Next
    INDEX
    Explanations

    customizer, widgets, custom menu, custom field, ID

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

    The neuron is looking for code snippets that use the WordPress Customizer API (e.g. “wp_customize”, “add_section”, “customizer.php” calls).

    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
    蓠
    -2.33
    ༷
    -1.75
     of
    -1.74
     overarching
    -1.64
     таких
    -1.60
    
    -1.59
     acht
    -1.58
    ("
    -1.57
     oito
    -1.55
    currently
    -1.50
    POSITIVE LOGITS
     kilom
    1.58
     myſelf
    1.55
     Monfieur
    1.54
     車場
    1.52
     esq
    1.47
     LUMI
    1.44
     zc
    1.44
     seder
    1.43
     celeste
    1.39
     fuq
    1.39
    Activations Density 0.019%

    No Known Activations