© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6771
    Prev
    Next
    INDEX
    Explanations

    dropdown select menus

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

    The neuron is highly activated by occurrences of the word “dropdown” (in code or configuration names).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    轳
    -3.89
    訁
    -2.95
    y
    -2.95
     одной
    -2.86
    蓠
    -2.66
     {
    -2.63
     This
    -2.56
    1
    -2.50
     Your
    -2.48
    ⻬
    -2.48
    POSITIVE LOGITS
    鷓
    2.95
    鄠
    2.84
    琤
    2.66
    玢
    2.61
    
    2.55
    鳧
    2.48
    涐
    2.47
     měla
    2.45
    鳢
    2.41
    些什么
    2.39
    Activations Density 0.009%

    No Known Activations