© 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. 43112
    Prev
    Next
    INDEX
    Explanations

    closing code blocks or object definitions

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

    The neuron activates on closing braces ( “}” ) typically followed by a semicolon—i.e. the ends of object or function declarations in code.

    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
    
    -1.78
    珢
    -1.57
    だそうです
    -1.52
    合适的
    -1.49
     电子
    -1.47
    nora
    -1.46
    を考える
    -1.45
    安裝
    -1.45
    ERRA
    -1.44
    處理
    -1.43
    POSITIVE LOGITS
    9
    1.84
     —
    1.76
    7
    1.66
     zcela
    1.59
     ‘
    1.57
     キャップ
    1.55
    0
    1.54
     několik
    1.52
     выбрать
    1.51
     «
    1.49
    Activations Density 0.028%

    No Known Activations