© 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. 41409
    Prev
    Next
    INDEX
    Explanations

    closing brackets and braces

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

    This neuron activates on square-bracket delimiters in code or data (i.e. list/array literal syntax).

    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
    If
    -2.00
    ichtete
    -1.99
    When
    -1.75
    UMENTO
    -1.72
    >
    -1.70
    <h3>
    -1.69
    ครื่อง
    -1.68
    It
    -1.66
    )、
    -1.66
    There
    -1.61
    POSITIVE LOGITS
    </b>
    2.39
    at
    2.38
     the
    2.33
    </h4>
    2.22
    笮
    2.08
    end
    2.06
     peuvent
    2.00
     they
    1.95
    of
    1.91
    ons
    1.91
    Activations Density 0.009%

    No Known Activations