© 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. 22-GEMMASCOPE-RES-131K
    7. 104552
    Prev
    Next
    INDEX
    Explanations

    code syntax

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

    This neuron detects the opening parenthesis that follows function or method names, i.e. marks function/method calls.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     clearColor
    -1.20
    ΤΕ
    -1.15
    （
    -1.13
    ྄
    -1.10
    ๔
    -1.08
     kiz
    -1.07
     não
    -1.06
     doch
    -1.05
    کت
    -1.05
    不着
    -1.04
    POSITIVE LOGITS
    CONTEN
    1.13
    CIUDAD
    1.12
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.06
     alanı
    1.06
     記
    1.05
    Manufact
    1.03
    Continu
    1.03
    Ruju
    1.02
    تصویر
    1.02
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.02
    Activations Density 0.009%

    No Known Activations