© 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. 60495
    Prev
    Next
    INDEX
    Explanations

    is a

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

    The neuron responds strongly to the copular verb “is” (especially in X “is” a Y definition sentences).

    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
    QPalette
    -0.83
     at
    -0.80
    欧
    -0.79
     Paz
    -0.75
     Vers
    -0.75
    🫶
    -0.73
     ngh
    -0.73
    岑
    -0.73
     European
    -0.73
     kultur
    -0.72
    POSITIVE LOGITS
    並ぶ
    0.85
    Malta
    0.85
     лучше
    0.82
    違った
    0.77
    詳しい
    0.76
    Karla
    0.75
     meilleures
    0.71
    ナチュラル
    0.71
     unicórnio
    0.70
    idł
    0.70
    Activations Density 0.063%

    No Known Activations