© 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. 39134
    Prev
    Next
    INDEX
    Explanations

    that is

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

    The neuron is a high-precision detector for the word “that.”

    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
     and
    -3.73
     that
    -3.16
     for
    -3.09
     to
    -2.98
    ৄ
    -2.92
     or
    -2.84
    ↑↑↑</
    -2.78
     took
    -2.75
     as
    -2.72
    ୈ
    -2.69
    POSITIVE LOGITS
    that
    4.47
    1
    3.28
    Basically
    3.27
    5
    3.13
    2
    3.13
    Whether
    2.89
    "
    2.83
    This
    2.83
    Specifically
    2.81
    4
    2.80
    Activations Density 0.003%

    No Known Activations