© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 124635
    Prev
    Next
    INDEX
    Explanations

    there is/are

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

    The neuron activates specifically on occurrences of the word “there,” especially in existential constructions (e.g. “there is/there are”).

    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
    w
    -1.86
    s
    -1.86
    也
    -1.77
    苙
    -1.66
    简称
    -1.66
    g
    -1.63
     straips
    -1.62
    柺
    -1.59
    ización
    -1.58
     \"
    -1.58
    POSITIVE LOGITS
    .
    2.00
    there
    1.86
     összefoglal
    1.74
    鹀
    1.70
    所以在
    1.67
     “(
    1.63
     Technically
    1.62
     the
    1.59
    这让
    1.59
     unterstützen
    1.56
    Activations Density 0.049%

    No Known Activations