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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84806
    Prev
    Next
    INDEX
    Explanations

    nations ending in Republic

    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
    eren
    -0.80
    lerc
    -0.79
    呼ば
    -0.78
    CAE
    -0.74
    liani
    -0.73
    zono
    -0.73
    Chips
    -0.72
    enskap
    -0.71
    ngh
    -0.71
    RIG
    -0.70
    POSITIVE LOGITS
     Republic
    1.65
    Republic
    1.37
     REPUBLIC
    1.14
     republic
    0.98
    atleta
    0.81
    راج
    0.81
    republic
    0.80
    ས།
    0.79
    Example
    0.77
     Republik
    0.76
    Activations Density 0.014%

    No Known Activations