© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2927
    Prev
    Next
    INDEX
    Explanations

    and

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

    The neuron is specifically detecting the 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
    。
    0.71
    ۔
    0.68
     misalnya
    0.66
    때
    0.58
    此外
    0.57
     например
    0.57
    ।
    0.57
    ։
    0.56
    ؛
    0.56
    ，
    0.55
    POSITIVE LOGITS
    ंगाबाद
    0.62
    romeda
    0.60
    rogens
    0.60
    蔼
    0.56
    အတူ
    0.55
    rog
    0.54
    ROID
    0.52
    藹
    0.51
     whatnot
    0.51
    रील
    0.50
    Activations Density 0.000%

    No Known Activations