© 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. 95368
    Prev
    Next
    INDEX
    Explanations

    sad face parenthesis code

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

    This neuron detects method or function signatures—especially the Objective-C style declarations with return‐type parentheses and colons (e.g. “- (void)drawRect:(CGRect)…”).

    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
     only
    -1.52
     all
    -1.13
    all
    -0.99
     each
    -0.99
    is
    -0.98
    度に
    -0.96
    隻
    -0.94
     '
    -0.94
    do
    -0.94
    并在
    -0.93
    POSITIVE LOGITS
     empie
    1.23
    Studi
    1.13
     hierbas
    1.11
     poliéster
    1.10
    точници
    1.09
    
    1.09
     nór
    1.09
    فران
    1.05
    prze
    1.04
    französ
    1.04
    Activations Density 0.008%

    No Known Activations