© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66880
    Prev
    Next
    INDEX
    Explanations

    HTML meta tags and UTF-8 encoding

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

    The neuron fires on HTML/XML metadata tags—especially `<meta charset="UTF-8">` declarations and related head‐element attributes (like link rel=stylesheet).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Ⅲ
    -1.20
    corrhi
    -1.18
    .”
    -1.18
    ₱
    -1.16
    <[
    -1.16
    넨
    -1.13
    ```
    -1.13
     "))
    -1.12
    ocarditis
    -1.11
    </h5>
    -1.09
    POSITIVE LOGITS
    <bos>
    1.22
    żeli
    1.22
    澁
    1.15
    ですが
    1.15
     одним
    1.13
     scatola
    1.13
     augen
    1.09
    rotten
    1.09
    が無
    1.07
    曖昧さ
    1.07
    Activations Density 0.003%

    No Known Activations