© 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. 22-GEMMASCOPE-RES-131K
    7. 127916
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on author‐to‐reader sharing language—especially the word “with” in phrases like “share … with you.”

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    sharing with you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Bios
    -1.02
     bios
    -1.01
     memeriksa
    -1.00
     erinner
    -0.97
     bài
    -0.90
    Յ
    -0.86
     версия
    -0.86
     hatır
    -0.84
    bA
    -0.84
     beliebt
    -0.84
    POSITIVE LOGITS
     others
    1.45
     you
    1.44
    thers
    1.06
    others
    1.05
     אחרים
    1.04
    everyone
    1.03
     kepada
    1.02
    Sharing
    0.99
     fellow
    0.99
     condividere
    0.96
    Activations Density 0.025%

    No Known Activations