© 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. 119383
    Prev
    Next
    INDEX
    Explanations

    words or phrases followed by punctuation

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

    This neuron detects the copula “to be” (e.g. “is” in English, “je” in Bosnian/Croatian, etc.) across different languages.

    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
    啭
    -1.81
    缃
    -1.78
    镡
    -1.76
     forState
    -1.75
     WRITING
    -1.74
    Ⴈ
    -1.72
    ᷇
    -1.67
     pady
    -1.67
     UIAlert
    -1.66
    ኻ
    -1.66
    POSITIVE LOGITS
     It
    2.89
     to
    2.83
     a
    1.88
    es
    1.84
     faceva
    1.81
    x
    1.77
     that
    1.76
     various
    1.75
     many
    1.67
     voleva
    1.66
    Activations Density 0.052%

    No Known Activations