© 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. 99008
    Prev
    Next
    INDEX
    Explanations

    names, especially Chinese names

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

    This neuron fires on capitalized name fragments (personal names).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    0
    -2.75
     ſch
    -2.48
     allarg
    -2.41
    寕
    -2.39
     We
    -2.39
     GOtt
    -2.36
    ('');
    -2.36
     fuff
    -2.33
     patiently
    -2.31
     Roughly
    -2.31
    POSITIVE LOGITS
    >--}}
    2.69
    玊
    2.61
    虓
    2.45
     tonnes
    2.41
     slumped
    2.31
    珧
    2.30
     ef
    2.23
     american
    2.16
    恭喜
    2.14
     metres
    2.11
    Activations Density 0.006%

    No Known Activations