© 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. 102528
    Prev
    Next
    INDEX
    Explanations

    Django admin and phpMyAdmin

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

    The neuron fires on occurrences of the token “admin” (in code or text).

    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
     focusing
    -0.73
     diversa
    -0.66
    皆様
    -0.65
    ᗜ
    -0.65
    MINUTES
    -0.65
     筆
    -0.64
    黄
    -0.64
    темати
    -0.63
    販
    -0.62
     pertin
    -0.62
    POSITIVE LOGITS
    鑊
    0.88
    irea
    0.85
    ServerError
    0.83
    covers
    0.81
     site
    0.77
    Lø
    0.77
     uy
    0.77
    Covers
    0.76
     eater
    0.75
    @{
    0.73
    Activations Density 0.032%

    No Known Activations