© 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. 34-GEMMASCOPE-RES-131K
    7. 1397
    Prev
    Next
    INDEX
    Explanations

    Objective-C message sends beginning with `[`

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

    The neuron is highly selective for code tokens—especially Objective-C method names, selectors, and language syntax elements.

    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
    
    -0.76
     adherents
    -0.75
     this
    -0.73
    ⌉
    -0.73
     dishon
    -0.72
    ๊
    -0.71
     '').
    -0.71
     swoją
    -0.71
    )$.
    -0.71
     ша
    -0.70
    POSITIVE LOGITS
     [
    2.59
    [
    1.96
    =[
    1.87
     $[
    1.69
    ([
    1.61
    -[
    1.52
     [_
    1.49
    ,[
    1.46
    +[
    1.45
    ',[
    1.45
    Activations Density 0.035%

    No Known Activations