© 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. 72143
    Prev
    Next
    INDEX
    Explanations

    by which

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

    This neuron detects occurrences of the relative pronoun “which” introducing explanatory or defining clauses.

    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
     '
    -1.78
     \_
    -1.77
     disminución
    -1.61
     „,
    -1.59
     aveva
    -1.59
     jaya
    -1.59
    会社の
    -1.58
    コミュニ
    -1.53
     paff
    -1.51
     yake
    -1.48
    POSITIVE LOGITS
     You
    1.78
    Surely
    1.75
    centiles
    1.72
    lgari
    1.70
    狃
    1.66
    Eventually
    1.65
     Would
    1.65
     Können
    1.64
    If
    1.63
     Quien
    1.62
    Activations Density 0.010%

    No Known Activations