© 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. 6736
    Prev
    Next
    INDEX
    Explanations

    explaining how something works

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

    The neuron strongly detects the phrase “Welcome to,” i.e. the introductory “Welcome to [X]” greeting that begins a page or section.

    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
     її
    0.82
     quei
    0.82
    quele
    0.79
    ik
    0.78
    ی
    0.78
    á
    0.78
    ід
    0.78
     şi
    0.77
    rilor
    0.76
    k
    0.75
    POSITIVE LOGITS
     因此
    0.77
     सेमीफाइनल
    0.74
     ==============
    0.73
     cemeteries
    0.70
    ...............
    0.69
     ۲۰۰
    0.69
     accuracies
    0.69
    ............
    0.68
    ުގެ
    0.68
    Semif
    0.68
    Activations Density 0.001%

    No Known Activations