© 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. 34-GEMMASCOPE-RES-131K
    7. 38607
    Prev
    Next
    INDEX
    Explanations

    foreign language phrases

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

    This neuron detects non-English (foreign-language) words or tokens 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_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
    "—
    -1.05
     two
    -1.03
    nictví
    -1.02
     große
    -1.00
     nahezu
    -1.00
     alongside
    -0.98
    钱包
    -0.98
     vermutlich
    -0.97
     啦
    -0.95
     In
    -0.93
    POSITIVE LOGITS
     colorear
    1.46
     XNUMX
    1.30
    tilizer
    1.29
    $^{
    1.23
     pierde
    1.22
    |}{\
    1.20
     цент
    1.20
     you
    1.20
     télécharger
    1.19
     fechar
    1.17
    Activations Density 0.020%

    No Known Activations