© 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. 45577
    Prev
    Next
    INDEX
    Explanations

    franchise and game names

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

    The neuron fires strongly on capitalized named entities—proper names of people, places, organizations, titles, and other similar tokens.

    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
    锨
    -1.52
     空港
    -1.50
     ayakkab
    -1.49
     eier
    -1.48
    襌
    -1.45
    鶿
    -1.43
    沵
    -1.43
    鶲
    -1.40
    閖
    -1.38
    镞
    -1.38
    POSITIVE LOGITS
     he
    1.52
     Witcher
    1.51
     Since
    1.45
     To
    1.44
     Because
    1.42
    livion
    1.38
     for
    1.37
    茄子
    1.34
     since
    1.31
    枇
    1.31
    Activations Density 0.003%

    No Known Activations