© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64018
    Prev
    Next
    INDEX
    Explanations

    nationalities and associated nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Not in Any Lists

    No Comments

    Negative Logits
    トーン
    -0.89
    Boiling
    -0.82
    丅
    -0.81
    čít
    -0.79
    putExtra
    -0.79
    arians
    -0.76
     Latvia
    -0.75
    Verde
    -0.75
    gypten
    -0.73
     крае
    -0.73
    POSITIVE LOGITS
     national
    1.06
     nationals
    0.99
     flag
    0.99
     総合
    0.98
     Government
    0.96
     nationwide
    0.96
     language
    0.93
     government
    0.93
    acán
    0.88
    ﾓ
    0.82
    Activations Density 0.071%

    No Known Activations