© 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. 34-GEMMASCOPE-RES-131K
    7. 822
    Prev
    Next
    INDEX
    Explanations

    PHP class names and properties

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

    This neuron fires on the parentheses in function definitions or calls (i.e. the “( )” tokens surrounding parameters).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    `]
    -0.92
    منى
    -0.78
    sandalias
    -0.75
    総合
    -0.75
    夙
    -0.73
    BaseController
    -0.72
     cucharada
    -0.71
    燁
    -0.71
    ၅
    -0.71
     Sabah
    -0.71
    POSITIVE LOGITS
     purcha
    0.75
    ゴリ
    0.75
     ($(
    0.74
    éhez
    0.73
     Πε
    0.73
     Conj
    0.73
    arar
    0.73
     grossesse
    0.72
     fallow
    0.72
     Cui
    0.71
    Activations Density 0.013%

    No Known Activations