© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5965
    Prev
    Next
    INDEX
    Explanations

    The neuron spotlights names of institutions, professional bodies, and analogous organizational or award titles.

    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_31_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
     Sauvignon
    0.55
    詡
    0.54
     हमने
    0.53
    வியில்
    0.53
     Alek
    0.52
    下滑
    0.52
     Pilot
    0.52
     Neymar
    0.52
    ワゴン
    0.51
    🦢
    0.51
    POSITIVE LOGITS
     Ministry
    1.74
     USAID
    1.71
     Kementerian
    1.66
     NOAA
    1.64
     UNESCO
    1.63
    Ministry
    1.63
     USDA
    1.62
     وزارة
    1.62
     Министерство
    1.57
     Ministerio
    1.55
    Activations Density 0.761%

    No Known Activations