© 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. 10-GEMMASCOPE-RES-131K
    7. 85466
    Prev
    Next
    INDEX
    Explanations

    HTML select elements and code selections

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

    This neuron activates on the literal token “select,” i.e. instances of the word “select” in code or markup (especially in HTML <select> tags and related 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
    ed
    -3.39
    </strong>
    -3.13
    ’
    -3.00
     
    -2.72
    na
    -2.45
    r
    -2.31
    на
    -2.28
    <i>
    -2.28
    u
    -2.17
    ir
    -2.14
    POSITIVE LOGITS
    懨
    2.73
    Ⲉ
    2.73
    ࿆
    2.64
    缑
    2.64
    نگار
    2.63
    噥
    2.61
    
    2.50
    ⛦
    2.42
    螃
    2.41
    ୈ
    2.41
    Activations Density 0.022%

    No Known Activations