© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 221449
    Prev
    Next
    INDEX
    Explanations

    Brazil

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

    Brazilian government

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Makassar
    0.46
     ちゃっ
    0.44
    แพ
    0.39
     decommissioning
    0.39
    والی
    0.37
     الفق
    0.37
    宁
    0.37
     Jakarta
    0.37
     toolPath
    0.37
    ަރު
    0.36
    POSITIVE LOGITS
     gays
    0.43
     stray
    0.42
    Orig
    0.41
    NZ
    0.40
     tart
    0.38
    焼
    0.38
    ]^{-
    0.37
    Ꮲ
    0.36
     thịt
    0.36
    𐰆
    0.36
    Activations Density 0.015%

    No Known Activations