© 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. 4983
    Prev
    Next
    INDEX
    Explanations

    concerning, about, regarding

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

    This neuron responds to mentions of the under-fill resin process—especially the filling (注入/充填) and curing (硬化) steps.

    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
    이다
    0.99
     합니다
    0.93
    입니다
    0.87
    です
    0.83
     입니다
    0.80
    진다
    0.79
    합니다
    0.77
    이에요
    0.74
    となります
    0.74
    になります
    0.73
    POSITIVE LOGITS
     અંગે
    1.17
    Regarding
    1.13
    时的
    1.12
    については
    1.09
    關於
    1.05
    に関しては
    1.03
    Concerning
    1.02
     පිළිබඳ
    1.01
    关于
    1.00
    に対する
    0.99
    Activations Density 0.014%

    No Known Activations