© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 92902
    Prev
    Next
    INDEX
    Explanations

    text changes and input

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

    This neuron detects code tokens naming or handling text‐change events (e.g. “TextChanged,” “onTextChanged,” “keyup,” etc.) in UI input controls.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     chale
    -1.15
     wanda
    -1.11
    next
    -1.10
     doos
    -1.10
     الاص
    -1.10
     contrats
    -1.09
     lele
    -1.06
     verba
    -1.05
     لكل
    -1.03
     ſou
    -1.01
    POSITIVE LOGITS
     changes
    1.13
     input
    1.12
     zwłaszcza
    1.09
     Ergän
    1.08
     ANYTHING
    1.05
     progressively
    1.04
    寝室
    1.03
    ئلة
    1.01
     $\
    0.98
     учетом
    0.98
    Activations Density 0.011%

    No Known Activations