© 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. 10-GEMMASCOPE-RES-131K
    7. 103982
    Prev
    Next
    INDEX
    Explanations

    bat followed by various endings

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

    The neuron strongly activates on occurrences of the substring “Batting” (e.g. in class or variable names like BattingStats) or its component tokens “Bat” and “ting.”

    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
    是她
    -2.94
     \_
    -2.92
    睃
    -2.70
    鸶
    -2.63
    已经有
    -2.61
    袛
    -2.44
    ꦫ
    -2.39
    ⁛
    -2.38
    𐄁
    -2.34
    艄
    -2.33
    POSITIVE LOGITS
    </i>
    4.28
    </strong>
    2.83
    '
    2.81
    {
    2.73
    y
    2.73
    </h1>
    2.72
    ,”
    2.70
     the
    2.61
     The
    2.61
    ";
    2.56
    Activations Density 0.007%

    No Known Activations