© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130152
    Prev
    Next
    INDEX
    Explanations

    as well as

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

    The neuron fires on the connective phrase “as well as.”

    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
    摇了
    -2.30
    薆
    -2.02
     retira
    -1.79
    ︲
    -1.78
    :^{
    -1.77
    ↵↵↵↵↵↵↵↵
    -1.77
    媗
    -1.75
    屙
    -1.74
    を使
    -1.73
     retorna
    -1.73
    POSITIVE LOGITS
    Sometimes
    1.99
    There
    1.95
     Also
    1.83
    Because
    1.82
     Usually
    1.81
    Did
    1.80
     Often
    1.79
    Often
    1.78
     Sometimes
    1.78
     Shouldn
    1.73
    Activations Density 0.019%

    No Known Activations