© 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. 6941
    Prev
    Next
    INDEX
    Explanations

    Filipino, Philippines

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

    The neuron flags terms referring to the Philippines—its places, people, language, currency, and related proper names.

    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
    Karin
    -1.33
    ALWAYS
    -1.29
     queridos
    -1.28
     different
    -1.28
     accompli
    -1.24
     farklı
    -1.23
     sév
    -1.22
     seznam
    -1.19
     hoặc
    -1.18
    和她
    -1.18
    POSITIVE LOGITS
     of
    1.45
     just
    1.16
    یزات
    1.10
    Just
    1.09
    A
    1.09
     dictate
    1.08
    РАВ
    1.08
    As
    1.08
     had
    1.07
    бри
    1.07
    Activations Density 0.077%

    No Known Activations