© 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. 4937
    Prev
    Next
    INDEX
    Explanations

    is trust communication

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

    The neuron strongly activates on words and phrases about love, romantic feelings, and relationship emotions.

    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
    🏭
    0.58
     volumetric
    0.57
     маль
    0.56
     citizens
    0.55
     obsc
    0.55
     obscur
    0.55
     Auctions
    0.54
    WebGL
    0.54
    市民
    0.54
     νό
    0.53
    POSITIVE LOGITS
    💑
    1.36
     marital
    1.30
     infidelity
    1.29
     divorce
    1.25
     Couples
    1.25
     Divorce
    1.24
     couples
    1.23
    marital
    1.23
    💏
    1.23
    離婚
    1.20
    Activations Density 0.593%

    No Known Activations