© 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. 16712
    Prev
    Next
    INDEX
    Explanations

    license exception

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

    This neuron fires on prominent domain‐specific nouns—often formal labels or section headings denoting institutions, roles, venues, or topics.

    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
    .”
    -1.79
    ’
    -1.38
    ”
    -1.36
    â
    -1.31
    ara
    -1.30
    co
    -1.30
    ,”
    -1.29
     The
    -1.26
    
    -1.22
    T
    -1.21
    POSITIVE LOGITS
    媖
    1.67
     kontinu
    1.50
     diskusi
    1.41
    legende
    1.35
    larınız
    1.34
     skupina
    1.33
     kosme
    1.31
     biela
    1.29
     telefonu
    1.29
     kılıf
    1.29
    Activations Density 0.275%

    No Known Activations