© 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. 79777
    Prev
    Next
    INDEX
    Explanations

    public class declarations

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

    The neuron identifies programming‐language structural keywords (e.g. access modifiers like “public,” interface/class declarations, braces) in code snippets.

    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
     if
    -1.20
    hamos
    -1.05
     it
    -0.95
    磬
    -0.95
    Источники
    -0.93
     仔
    -0.91
     as
    -0.90
     обеспечить
    -0.88
    متن
    -0.86
     ڤ
    -0.85
    POSITIVE LOGITS
     religieux
    0.99
    剧本
    0.93
     jendela
    0.93
     professeurs
    0.92
    𝑞
    0.91
    Liên
    0.91
     bezw
    0.91
     dzięki
    0.90
     daugiau
    0.89
     jūsų
    0.88
    Activations Density 0.142%

    No Known Activations