© 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. 105037
    Prev
    Next
    INDEX
    Explanations

    recognizer

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

    the word "Recognizer" in technical or programming contexts.

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

    This neuron detects occurrences of “recognizer” (especially gesture‐ or regex‐recognizer class names) in code snippets.

    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
    _{
    -2.97
    ╿
    -2.64
    это
    -2.52
    噥
    -2.45
     ruinas
    -2.45
    0
    -2.41
    螽
    -2.36
    咵
    -2.33
     tries
    -2.27
     ingenious
    -2.25
    POSITIVE LOGITS
     stark
    2.67
    祤
    2.59
    臈
    2.56
    
    2.45
    皝
    2.42
     уровне
    2.38
    摀
    2.30
    
    2.30
     そば
    2.30
     unsere
    2.30
    Activations Density 0.001%

    No Known Activations