© 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. 130818
    Prev
    Next
    INDEX
    Explanations

    setting or reading HTML content

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

    The neuron fires on references to an element’s “inner” content properties (e.g. innerHTML or innerText).

    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
    A
    -2.64
    綣
    -2.28
    C
    -2.23
    1
    -2.23
    ጪ
    -2.22
    Y
    -2.17
    with
    -2.11
    2
    -2.00
     知道
    -2.00
     出
    -2.00
    POSITIVE LOGITS
    嗵
    2.56
    神
    2.50
    蹰
    2.38
    cún
    2.34
     cocin
    2.23
    霂
    2.22
    幪
    2.19
    垰
    2.19
    颏
    2.19
    縂
    2.17
    Activations Density 0.002%

    No Known Activations