© 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. 34-GEMMASCOPE-RES-131K
    4. 110867
    Prev
    Next
    INDEX
    Explanations

    double followed by specific words

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

    The neuron detects occurrences of the substring “double” (in any capitalization or as part of compound tokens) across the text.

    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
    撬
    -1.01
    要不然
    -1.00
     Melhor
    -0.94
    skyl
    -0.90
     буду
    -0.87
     Füßen
    -0.85
     crumbled
    -0.84
     Mientras
    -0.83
    Glorious
    -0.82
    可以说
    -0.82
    POSITIVE LOGITS
    double
    1.70
    Double
    1.52
     sided
    1.41
     double
    1.34
     dbl
    1.33
     Double
    1.32
     decker
    1.31
    getDouble
    1.27
     PRECISION
    1.23
    双
    1.23
    Activations Density 0.028%

    No Known Activations