© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102342
    Prev
    Next
    INDEX
    Explanations

    exception handling

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

    closing braces in code blocks.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron detects closing‐block punctuation in code—especially the “}” braces (often with trailing semicolons or brackets) that end functions, objects, or arrays.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    硖
    -1.66
     เป็น
    -1.57
    СИ
    -1.56
     if
    -1.54
     neighbouring
    -1.52
    ická
    -1.50
    словия
    -1.49
    ÓN
    -1.48
     neighboring
    -1.47
     it
    -1.46
    POSITIVE LOGITS
    These
    2.06
    3
    2.03
    7
    1.94
    0
    1.92
    9
    1.91
    k
    1.90
    It
    1.79
    8
    1.77
    es
    1.76
    這些
    1.75
    Activations Density 0.009%

    No Known Activations