© 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. 5123
    Prev
    Next
    INDEX
    Explanations

    each other

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

    The neuron fires on phrases expressing reciprocal interaction, in particular the words “each other.”

    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
     Alongside
    0.64
     Payload
    0.60
    Alongside
    0.57
    соеди
    0.56
    Picture
    0.54
    مره
    0.52
     રહ્યો
    0.52
    Stride
    0.52
    是一名
    0.52
    嘆
    0.52
    POSITIVE LOGITS
     birbir
    2.88
     nhau
    2.83
     elkaar
    2.77
    彼此
    2.75
     друг
    2.63
     egym
    2.47
    互相
    2.36
     서로
    2.36
    กัน
    2.33
     mutually
    2.25
    Activations Density 0.384%

    No Known Activations