© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22208
    Prev
    Next
    INDEX
    Explanations

    that + [clause introducer]

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

    The neuron strongly activates on instances of 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
    きち
    -1.95
     Inſ
    -1.94
    ごめんなさい
    -1.91
     then
    -1.89
    ごちそう
    -1.88
    細かく
    -1.86
    וץ
    -1.84
    卺
    -1.84
    鹩
    -1.81
    INOIS
    -1.80
    POSITIVE LOGITS
    1
    2.22
    4
    2.11
    m
    2.09
    as
    2.02
    2
    1.99
     Having
    1.91
    This
    1.85
    就
    1.77
    S
    1.76
    =
    1.76
    Activations Density 0.012%

    No Known Activations