© 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. 6861
    Prev
    Next
    INDEX
    Explanations

    objective-c method calls

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

    This neuron detects Objective-C selector names (i.e. multi-word Cocoa/UIKit method identifiers).

    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
     would
    -0.93
     provide
    -0.90
    rierten
    -0.88
     from
    -0.85
     and
    -0.83
     Sloveniji
    -0.81
    (),
    -0.81
    (['/
    -0.81
    監督
    -0.80
    ensis
    -0.80
    POSITIVE LOGITS
    :
    1.17
    Ohne
    0.92
     Ministre
    0.90
    THAT
    0.89
     espagnol
    0.88
     ministre
    0.88
     aast
    0.87
    ⊡
    0.85
     içeris
    0.85
     Secrétaire
    0.84
    Activations Density 0.008%

    No Known Activations