© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15293
    Prev
    Next
    INDEX
    Explanations

    This neuron detects programming identifiers and library or class names, particularly CamelCase tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    cosec
    0.65
     бути
    0.62
     =,
    0.61
     НА
    0.61
     fasted
    0.60
     UAE
    0.59
    eonium
    0.59
     начать
    0.59
    ⓡ
    0.59
    ដល់
    0.58
    POSITIVE LOGITS
    LException
    0.76
    DataManager
    0.68
     implements
    0.67
    Utils
    0.66
     Runnable
    0.61
    Object
    0.61
    Runnable
    0.61
    此类
    0.59
     Manager
    0.59
    クラス
    0.59
    Activations Density 0.015%

    No Known Activations