© 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. 130552
    Prev
    Next
    INDEX
    Explanations

    English language or translations

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

    The neuron detects occurrences of language names (e.g. English, Russian, Japanese, etc.) in 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_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
     hijas
    -1.85
     in
    -1.60
     Of
    -1.57
     Präsidenten
    -1.56
     немец
    -1.53
    𝗜
    -1.52
    koszulka
    -1.50
     vieja
    -1.49
     kancel
    -1.49
     We
    -1.48
    POSITIVE LOGITS
    With
    2.00
    .
    1.95
    Even
    1.93
    地说
    1.85
    which
    1.80
    Most
    1.71
    就是
    1.71
    Despite
    1.69
    Following
    1.68
    Without
    1.67
    Activations Density 0.022%

    No Known Activations