© 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. 22-GEMMASCOPE-RES-131K
    7. 26885
    Prev
    Next
    INDEX
    Explanations

    code structure declarations

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

    The neuron detects C-style code syntax elements (e.g. braces, semicolons, keywords like int or method names) that mark the start/end of code blocks.

    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
     at
    -1.09
     menghadapi
    -1.01
     gikk
    -1.00
    
    -0.97
     frère
    -0.94
    Fordítás
    -0.91
    我们
    -0.90
    arque
    -0.89
    بال
    -0.87
    éfonos
    -0.86
    POSITIVE LOGITS
    当我
    0.96
    ash
    0.96
    这几
    0.96
    诶
    0.91
    这点
    0.85
    かっこいい
    0.85
     beschrieben
    0.84
    ashing
    0.82
    ites
    0.81
    これだけ
    0.81
    Activations Density 0.011%

    No Known Activations