© 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. 83897
    Prev
    Next
    INDEX
    Explanations

    introducing personal viewpoints

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

    The neuron detects the phrase “For me” (marking a shift to a first-person opinion).

    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
     in
    -1.70
    癡
    -1.66
    ־ה
    -1.62
     several
    -1.59
    usstsein
    -1.59
    Avenue
    -1.54
     on
    -1.52
     Forscher
    -1.50
     studie
    -1.48
     various
    -1.47
    POSITIVE LOGITS
     it
    1.60
    再度
    1.53
     désir
    1.51
    begin
    1.48
     就是
    1.47
     which
    1.44
     coût
    1.34
     paſſ
    1.34
    которые
    1.34
     说
    1.33
    Activations Density 0.008%

    No Known Activations