© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98263
    Prev
    Next
    INDEX
    Explanations

    Chinese followed by specific entities

    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
    inians
    -0.96
     China
    -0.93
    ATCH
    -0.92
    zando
    -0.87
     Countries
    -0.85
    HOUSE
    -0.82
     abenço
    -0.81
     HDF
    -0.80
    obb
    -0.79
    たちに
    -0.79
    POSITIVE LOGITS
     were
    0.91
     themselves
    0.88
    (´
    0.85
     nationals
    0.85
     whispers
    0.84
     people
    0.82
     »
    0.79
    陛
    0.79
    kező
    0.78
     version
    0.75
    Activations Density 0.027%

    No Known Activations