© 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. 1465
    Prev
    Next
    INDEX
    Explanations

    question words followed by verbs

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

    The neuron strongly activates on occurrences of the question word “Why,” flagging question prompts.

    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
     તમે
    0.68
     Rússia
    0.62
     you
    0.61
     Špan
    0.61
     YOU
    0.61
     bạn
    0.59
     ਤੁਸੀਂ
    0.59
     你
    0.57
     Jezus
    0.57
    你
    0.56
    POSITIVE LOGITS
     ensure
    0.59
     distribute
    0.55
     ensures
    0.55
    ではなく
    0.54
     cannot
    0.52
    并非
    0.52
     for
    0.51
     create
    0.51
    并不是
    0.51
     as
    0.50
    Activations Density 0.005%

    No Known Activations