© 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. 4450
    Prev
    Next
    INDEX
    Explanations

    and then

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

    The neuron strongly activates on the coordinating conjunction “and.”

    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
    お
    0.82
    ただし
    0.74
     그러나
    0.73
    그러나
    0.73
    你
    0.73
     misalnya
    0.72
    з
    0.71
     например
    0.70
    ю
    0.69
    例如
    0.68
    POSITIVE LOGITS
     sebagainya
    1.02
     whatnot
    0.99
    ंगाबाद
    0.88
    ERSON
    0.86
    ppure
    0.83
     tampoco
    0.76
    rogens
    0.73
    ROID
    0.73
    or
    0.72
     पनि
    0.72
    Activations Density 0.797%

    No Known Activations