© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101494
    Prev
    Next
    INDEX
    Explanations

    class builder API usage

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

    the word "Builder" in programming code, particularly in Java and C# class and method names.

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

    The neuron fires on occurrences of “Builder” (or class/method names ending in “Builder”) 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_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
     巾
    -1.66
    ADORES
    -1.56
     две
    -1.52
    🏟
    -1.49
    !),
    -1.47
     första
    -1.46
    辚
    -1.45
    welche
    -1.44
     {
    
    
    -1.44
     Ре
    -1.44
    POSITIVE LOGITS
     considerazione
    1.84
     additionally
    1.67
    噲
    1.62
    亊
    1.59
    ༈
    1.58
    >
    1.57
    はお
    1.55
    jalanan
    1.55
    h
    1.54
    媜
    1.52
    Activations Density 0.000%

    No Known Activations