© 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. 64290
    Prev
    Next
    INDEX
    Explanations

    you and your

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

    The neuron is detecting common function words—especially high-frequency prepositions, pronouns, and other “stop” words.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     themselves
    -2.14
     ihren
    -1.65
     lorsqu
    -1.60
     leurs
    -1.56
     ihrer
    -1.53
     ihres
    -1.49
     himself
    -1.40
    Their
    -1.37
     ihrem
    -1.36
     itself
    -1.34
    POSITIVE LOGITS
     your
    6.00
     yourself
    3.72
     you
    2.55
    your
    2.36
    yourself
    2.25
    Your
    2.11
     or
    2.06
     youre
    1.92
    你的
    1.75
    あなたの
    1.72
    Activations Density 0.052%

    No Known Activations