© 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. 15724
    Prev
    Next
    INDEX
    Explanations

    socket and includes

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

    The neuron consistently fires on occurrences of the word “Instant.”

    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
    nič
    0.61
     ബ്ല
    0.60
    літи
    0.59
     味
    0.58
    咊
    0.57
    trimenti
    0.57
     quests
    0.56
    nick
    0.55
    Zag
    0.55
    ческой
    0.55
    POSITIVE LOGITS
     Unique
    0.59
     Acceleration
    0.57
     hc
    0.57
     Warming
    0.55
    ตน
    0.55
     ($\
    0.54
     Concerning
    0.54
    តុ
    0.54
    Unique
    0.54
     ketua
    0.54
    Activations Density 0.002%

    No Known Activations