© 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. 81517
    Prev
    Next
    INDEX
    Explanations

    county seat or capital

    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
    ご購入
    -0.82
    ビーチ
    -0.79
    aliere
    -0.77
    锏
    -0.75
    خيص
    -0.74
    今回も
    -0.74
    Leírás
    -0.73
    ଵ
    -0.73
    ULE
    -0.73
    個室
    -0.71
    POSITIVE LOGITS
     capital
    6.41
    capital
    5.06
    Capital
    4.69
     Capital
    4.59
     CAPITAL
    4.19
     столи
    4.09
     capitals
    4.03
     capitale
    3.94
    CAPITAL
    3.86
     capitol
    3.80
    Activations Density 0.123%

    No Known Activations