© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106521
    Prev
    Next
    INDEX
    Explanations

    HTML content access

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

    This neuron identifies fragments of code or markup syntax (e.g. punctuation, HTML/JS keywords, braces, dots, parentheses) within the 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
    setCellStyle
    -0.81
    keypress
    -0.75
    ల
    -0.71
    Kerala
    -0.68
    Ting
    -0.68
    кость
    -0.66
     описание
    -0.66
    nye
    -0.65
     技術
    -0.65
    чную
    -0.64
    POSITIVE LOGITS
     inner
    3.66
    innerHTML
    2.86
     text
    2.84
     Inner
    2.67
    inner
    2.59
    innerText
    2.59
    Inner
    2.56
    textContent
    2.39
    text
    2.31
     INNER
    2.17
    Activations Density 0.064%

    No Known Activations