© 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. 10-GEMMASCOPE-RES-131K
    4. 3592
    Prev
    Next
    INDEX
    Explanations

    meta tags and headers

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

    The neuron detects HTML “head” metadata elements—especially link and meta tags for icons (favicon, apple-touch-icon), viewport settings, theme-color, robots directives, 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_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
    père
    -1.18
     ratón
    -1.17
    ]);
    
    -1.17
     is
    -1.15
     será
    -1.13
    薏
    -1.13
    %</
    -1.12
    伈
    -1.12
    |$.
    -1.09
     ナイ
    -1.08
    POSITIVE LOGITS
     first
    1.26
    諍
    1.16
     через
    1.14
     явля
    1.14
     melalui
    1.13
    /*"
    1.13
     ヶ
    1.11
    ulás
    1.10
    There
    1.10
     all
    1.10
    Activations Density 0.144%

    No Known Activations