© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20903
    Prev
    Next
    INDEX
    Explanations

    international words and phrases

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

    The neuron fires on content nouns (especially technical or topic-specific nouns) across different contexts.

    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
    ↵
    -3.16
     unruly
    -2.72
     unrelenting
    -2.58
    昻
    -2.56
     был
    -2.47
    愎
    -2.42
     $^{
    -2.41
     removes
    -2.39
     impressive
    -2.39
    but
    -2.39
    POSITIVE LOGITS
     anderen
    2.92
    ⃙
    2.73
     améli
    2.69
    闥
    2.66
     engender
    2.64
    鯓
    2.55
     Ensuring
    2.50
    焿
    2.39
    甃
    2.34
    .'
    2.30
    Activations Density 0.004%

    No Known Activations