© 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. 20266
    Prev
    Next
    INDEX
    Explanations

    conjunctions and adverbs

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

    The neuron strongly activates on Spanish and Portuguese discourse-marking adverbs (e.g. “también,” “después,” “então,” “alguém”).

    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
     votre
    -3.09
     nurture
    -2.80
     YOUR
    -2.56
    原因
    -2.55
     WITH
    -2.55
     desastre
    -2.52
     anderen
    -2.50
     当
    -2.47
     `
    -2.41
     télécommande
    -2.39
    POSITIVE LOGITS
    vantaged
    2.88
    ྥ
    2.78
    .
    2.72
    淠
    2.48
    <bos>
    2.42
    酲
    2.41
    Ꭳ
    2.41
    蚡
    2.36
    齷
    2.34
    龊
    2.27
    Activations Density 0.000%

    No Known Activations