© 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. 5479
    Prev
    Next
    INDEX
    Explanations

    providing explanations or instructions

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

    This neuron detects discourse markers that introduce steps or list items in instructions—phrases like “the one thing left,” “the second thing we need,” or “the next point you’ll need.”

    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
     TVs
    0.66
    孩子们
    0.66
     JIM
    0.65
     MPS
    0.65
     MSU
    0.64
     misalnya
    0.64
    的孩子
    0.64
     SSD
    0.63
     MSS
    0.63
     MIM
    0.63
    POSITIVE LOGITS
    either
    0.68
     trebuie
    0.63
    tul
    0.63
    econ
    0.63
    จะต้อง
    0.63
    now
    0.62
    са
    0.61
     selles
    0.60
    VEL
    0.59
     потрібно
    0.59
    Activations Density 0.000%

    No Known Activations