© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10331
    Prev
    Next
    INDEX
    Explanations

    creating objects or instances

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

    The neuron fires on programming or library identifiers (function, class, or API names and related keywords) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    technical documentation and code discussions, particularly focusing on object-oriented programming concepts like classes, objects, methods, and constructors.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    references to programming APIs—mentions of classes, objects/modules, instances, and constructors in code-focused explanations or documentation.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     symmetries
    0.62
     Unix
    0.61
     proliferating
    0.59
     Cows
    0.57
     Wikipedia
    0.57
     Python
    0.56
     symmetry
    0.56
     Kerr
    0.56
     listings
    0.56
     Makefile
    0.56
    POSITIVE LOGITS
    实例化
    1.20
    インスタ
    1.17
     экзем
    1.16
    对象
    1.16
     객
    1.16
    对象的
    1.09
     экземпля
    1.09
    オブジェクト
    1.09
     объекта
    1.08
    객
    1.05
    Activations Density 0.073%

    No Known Activations