© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83810
    Prev
    Next
    INDEX
    Explanations

    each other / one another

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

    The neuron fires on the two-word reciprocal phrase “each other.”

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     is
    -2.53
    o
    -1.81
     and
    -1.78
    櫚
    -1.78
     them
    -1.77
    自分が
    -1.76
    S
    -1.73
    榈
    -1.73
    繃
    -1.72
    L
    -1.71
    POSITIVE LOGITS
    毉
    1.96
    鹮
    1.95
    幃
    1.91
    꿩
    1.89
    땃
    1.88
     manj
    1.84
    縂
    1.81
    塒
    1.80
     for
    1.80
     between
    1.77
    Activations Density 0.009%

    No Known Activations