© 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. 12974
    Prev
    Next
    INDEX
    Explanations

    US, countdown, floats, town, human

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

    The neuron strongly fires on the final token of each text segment, effectively marking end-of-document (or end-of-span) boundaries.

    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
     deepened
    0.71
     deepen
    0.70
     Результа
    0.68
     препарата
    0.67
    洸
    0.66
     начал
    0.66
     ボー
    0.66
     工程
    0.64
    arte
    0.64
    ᴡ
    0.64
    POSITIVE LOGITS
     eBooks
    0.79
     buyout
    0.78
    تر
    0.76
     Smithsonian
    0.75
     amma
    0.75
    intendent
    0.75
    的重要
    0.73
     origami
    0.73
    ব্রিটিশ
    0.72
     दिसंबर
    0.71
    Activations Density 0.000%

    No Known Activations