© 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. 85817
    Prev
    Next
    INDEX
    Explanations

    english language identifier

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

    The neuron fires on language‐code tokens in HTML’s `<html lang="…">` attribute (e.g. “en” or “US”).

    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
     the
    -1.64
     знают
    -1.56
     own
    -1.51
     then
    -1.47
     terão
    -1.45
     become
    -1.42
    ᚔ
    -1.39
     extremely
    -1.38
     to
    -1.36
    了不少
    -1.34
    POSITIVE LOGITS
    <bos>
    1.76
    辉煌
    1.58
     epitome
    1.57
     összefoglal
    1.48
     بودند
    1.45
     badass
    1.45
     menatap
    1.45
    га
    1.44
     AWESOME
    1.44
     शुर
    1.42
    Activations Density 0.005%

    No Known Activations