© 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. 10-GEMMASCOPE-RES-131K
    7. 65448
    Prev
    Next
    INDEX
    Explanations

    xhtml code tags

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

    The neuron fires on technology/library/language names—especially tokens like Python‐package names (e.g. “pyxl”), markup languages (e.g. “xhtml”), or other software/tool identifiers.

    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
    瑧
    -2.42
    韞
    -2.33
    </h2>
    -2.33
    辚
    -2.25
     or
    -2.25
    </h4>
    -2.20
    ⻄
    -2.19
    ！　
    -2.17
     промышлен
    -2.17
    鳯
    -2.16
    POSITIVE LOGITS
    <bos>
    2.66
    s
    2.58
    ’
    2.58
    鱨
    2.27
     美甲
    2.22
    ндарт
    2.19
    在
    2.17
    
    2.17
    已经
    2.08
    кой
    2.03
    Activations Density 0.002%

    No Known Activations