© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5097
    Prev
    Next
    INDEX
    Explanations

    take place, take off, take over, take on

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

    This neuron strongly activates on the verb “take” (and its morphological variants like “takes” and “taking”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     সেটা
    0.48
    টাও
    0.48
     બધા
    0.48
    놔
    0.47
     annunci
    0.47
     صلاحیت
    0.46
    )_{
    0.45
     letting
    0.45
    iffany
    0.45
    वाही
    0.44
    POSITIVE LOGITS
     gerçekleştir
    0.51
     wówczas
    0.48
    ʿ
    0.48
     gerçekleşt
    0.47
     πραγ
    0.45
     menjalani
    0.43
     uczest
    0.43
     jointly
    0.42
    Microelectronics
    0.42
     bestaan
    0.41
    Activations Density 0.179%

    No Known Activations