© 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. 13118
    Prev
    Next
    INDEX
    Explanations

    of [possessive]

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

    This neuron fires on words naming aspects of living and bodily conditions (e.g. “lives,” “lifespan,” “circulatory systems,” “health”).

    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
    在一个
    0.57
     waktu
    0.54
    ሎችን
    0.53
    总体
    0.53
    ヨ
    0.52
    绝对
    0.51
    𒈬
    0.51
    在這個
    0.49
    佞
    0.49
    குறித்து
    0.49
    POSITIVE LOGITS
     of
    1.64
     của
    1.51
     của
    1.45
     ofthe
    1.39
    ของ
    1.37
     של
    1.23
     των
    1.05
     της
    1.05
    ຂອງ
    1.03
    របស់
    1.02
    Activations Density 0.000%

    No Known Activations