© 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. 24-GEMMASCOPE-2-RES-16K
    7. 7774
    Prev
    Next
    INDEX
    Explanations

    traditional teachings

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

    This neuron fires on mentions of sourcing or obtaining content from the “internet.”

    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
     retraction
    0.82
    诰
    0.78
    derabad
    0.71
     янва
    0.70
    жмите
    0.67
    уро
    0.67
     vesicular
    0.67
     siRNA
    0.66
    ycor
    0.66
     ديسمبر
    0.65
    POSITIVE LOGITS
     আশে
    0.75
    ⎪
    0.73
    ka
    0.72
     enemigos
    0.72
    ᴍ
    0.72
    mages
    0.71
    🐉
    0.71
     Enemies
    0.70
     eigentlich
    0.68
    的主
    0.67
    Activations Density 0.000%

    No Known Activations