© 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. 112267
    Prev
    Next
    INDEX
    Explanations

    parenthesized abbreviations

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

    The neuron strongly activates on standalone “)” tokens—i.e. the closing parenthesis that ends parenthetical acronyms, abbreviations, or other parenthetical material.

    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
     the
    -2.45
    敺
    -1.91
    ▿
    -1.85
     estadounid
    -1.83
     volle
    -1.76
    烀
    -1.70
    sandalia
    -1.70
     -"
    -1.69
     reutiliz
    -1.69
     می‌توان
    -1.68
    POSITIVE LOGITS
    </h3>
    1.71
     \
    1.63
    ization
    1.61
    ’,
    1.59
     &
    1.58
    atsby
    1.52
     to
    1.50
    Almost
    1.47
     กับ
    1.46
    (;;)
    1.46
    Activations Density 0.265%

    No Known Activations