© 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. 84557
    Prev
    Next
    INDEX
    Explanations

    WordPress themes and VC

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

    The neuron is picking up bits of file‐path and URL strings (slashes, directory names like “wp‐content,” themes, hyphens, numbers, etc.), i.e. code‐style path components.

    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
     ноября
    -0.75
    jectories
    -0.72
     Blink
    -0.72
    襲
    -0.71
     Бог
    -0.70
     Bevölkerung
    -0.70
     sump
    -0.68
     Богу
    -0.68
    啡
    -0.68
     sobr
    -0.67
    POSITIVE LOGITS
     theme
    1.07
     VC
    0.94
     THEME
    0.90
    vc
    0.88
    theme
    0.87
     ТЕ
    0.84
     WOOD
    0.81
    crum
    0.79
     vc
    0.78
     Vc
    0.76
    Activations Density 0.046%

    No Known Activations