© 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. 82742
    Prev
    Next
    INDEX
    Explanations

    wp-content/plugins or themes

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

    The neuron activates on tokens from WordPress file‐path URLs—specifically those containing “wp‐content” (and adjacent separators).

    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
    zionare
    -0.80
     düşün
    -0.78
     Small
    -0.74
    WERS
    -0.73
    quierda
    -0.72
     by
    -0.71
     provided
    -0.71
     options
    -0.69
     mutta
    -0.69
     although
    -0.68
    POSITIVE LOGITS
    uploads
    1.52
    themes
    1.18
     uploads
    1.12
     themes
    1.01
    THEME
    0.96
     Themes
    0.96
    plugins
    0.94
     RATING
    0.90
    Themes
    0.90
    originally
    0.89
    Activations Density 0.007%

    No Known Activations