© 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. 10495
    Prev
    Next
    INDEX
    Explanations

    key, Exit, broadcast

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

    The neuron strongly activates on mentions of the Laravel PHP web framework and its related technical terms.

    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
    িনীত
    0.61
    Suppl
    0.58
     あ
    0.57
    icana
    0.57
    Burger
    0.55
     ئ
    0.53
     قط
    0.53
    |[
    0.53
    Fract
    0.53
    Ữ
    0.53
    POSITIVE LOGITS
    ebel
    0.52
    getKey
    0.51
     Chevalier
    0.51
     Xiao
    0.50
    ലേ
    0.50
     взаимодействия
    0.50
     Doherty
    0.50
    ecimento
    0.50
     McMaster
    0.49
     बो
    0.49
    Activations Density 0.007%

    No Known Activations