© 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. 104023
    Prev
    Next
    INDEX
    Explanations

    ui elements and code structure

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

    the term "ui" (user interface) in code and technical documentation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron activates on occurrences of the sequence “ui” (as in UI or .ui identifiers) in code or markup.

    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
     porque
    -1.45
     ongoing
    -1.39
    知名
    -1.37
    {
    -1.37
     if
    -1.35
    同上
    -1.35
     vita
    -1.34
     tentar
    -1.34
     Ähn
    -1.32
     koska
    -1.30
    POSITIVE LOGITS
     antworte
    1.58
     alebo
    1.53
    涷
    1.51
    後的
    1.47
    一说
    1.46
    itizing
    1.45
     onPostExecute
    1.44
    ⎆
    1.40
    畕
    1.38
    評價
    1.38
    Activations Density 0.000%

    No Known Activations