© 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. 34-GEMMASCOPE-RES-131K
    4. 56095
    Prev
    Next
    INDEX
    Explanations

    object creation and initialization

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

    The neuron detects CamelCase identifiers (e.g. Objective-C class and method names) in code.

    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
     (
    -1.31
    قدام
    -1.11
    ='.$
    -0.98
    /",
    -0.93
     desapar
    -0.92
    ())
    
    -0.89
     練習
    -0.89
    /',
    -0.87
    期间
    -0.87
    ۞
    -0.86
    POSITIVE LOGITS
     with
    1.55
    :
    1.39
    తో
    1.07
    FontOfSize
    1.00
    :@"
    0.99
    ];
    0.98
    :[
    0.96
     for
    0.96
     với
    0.91
    БИ
    0.89
    Activations Density 0.027%

    No Known Activations