© 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. 34-GEMMASCOPE-RES-131K
    7. 56806
    Prev
    Next
    INDEX
    Explanations

    title, search, survey, closing

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

    The neuron is detecting proper‐noun sequences naming companies or corporate/organizational entities (e.g. title companies and similar service providers).

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     physiologic
    -0.84
     Physiological
    -0.78
     retinal
    -0.75
     Pesca
    -0.75
    สาม
    -0.72
     physiological
    -0.71
     balık
    -0.71
     autonomic
    -0.70
     الأربع
    -0.70
    setTexture
    -0.69
    POSITIVE LOGITS
     title
    1.05
     searcher
    1.02
     abstra
    0.98
     search
    0.98
     searches
    0.95
    搜索
    0.93
     searched
    0.90
     搜索
    0.88
     wygląda
    0.87
    setSearch
    0.84
    Activations Density 0.018%

    No Known Activations