© 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. 72087
    Prev
    Next
    INDEX
    Explanations

    as well as introductions

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

    The neuron fires specifically on instances of the multi-word connector “as well as.”

    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
     their
    -2.17
     if
    -1.94
    9
    -1.93
    7
    -1.88
    8
    -1.84
     more
    -1.72
    商品の
    -1.69
     probably
    -1.60
     should
    -1.55
     truly
    -1.55
    POSITIVE LOGITS
    釤
    1.80
    銠
    1.62
    IFT
    1.62
    وارض
    1.61
    rógeno
    1.61
    嵎
    1.61
    榈
    1.59
    quelles
    1.59
    ⧉
    1.58
    реи
    1.56
    Activations Density 0.013%

    No Known Activations