© 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. 34-GEMMASCOPE-RES-131K
    7. 115630
    Prev
    Next
    INDEX
    Explanations

    button types

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

    The neuron is keyed to code tokens defining or referring to “button” (e.g. CSS/SCSS selectors and class‐name fragments involving “button” and hyphens).

    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
    urou
    -0.93
    لاک
    -0.90
    ENODE
    -0.86
     Kläger
    -0.83
     تصویر
    -0.81
     シングル
    -0.81
    EMBRE
    -0.80
    väll
    -0.80
    tyard
    -0.79
    putString
    -0.79
    POSITIVE LOGITS
     secondary
    1.47
     outlined
    1.38
     button
    1.34
     primary
    1.31
     Button
    1.27
    secondary
    1.26
     outline
    1.17
    outline
    1.17
     btn
    1.15
     BUTTON
    1.14
    Activations Density 0.022%

    No Known Activations