© 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. 7989
    Prev
    Next
    INDEX
    Explanations

    code element selectors

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

    This neuron responds to uppercase technical keywords and commands—especially those used in automation scripts and error/log messages.

    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_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
     ゼ
    0.57
     "$
    0.57
    자동차
    0.55
     शूटिंग
    0.53
    SNS
    0.53
     webbrowser
    0.52
     kurulum
    0.52
     షూ
    0.52
    푸
    0.51
     Pages
    0.50
    POSITIVE LOGITS
    webElement
    0.61
    matchCondition
    0.59
    webElementGuid
    0.57
     степень
    0.55
     результа
    0.53
     словарь
    0.52
     رک
    0.50
     insulted
    0.50
     theta
    0.50
     neutralized
    0.50
    Activations Density 0.017%

    No Known Activations