© 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. 2320
    Prev
    Next
    INDEX
    Explanations

    Kazakhstan and Kyrgyzstan

    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
    ::~
    -0.83
     саны
    -0.81
    ליה
    -0.79
    Josef
    -0.76
    =[[
    -0.75
    凳
    -0.73
    வர
    -0.71
    ggior
    -0.69
     ~=
    -0.69
    ~=
    -0.69
    POSITIVE LOGITS
     Kazakhstan
    1.63
     Kaz
    1.37
    Kazakhstan
    1.27
     Казах
    1.21
     LLP
    1.09
     Қ
    1.09
     Shy
    1.06
     KZ
    1.05
    KZ
    0.96
     Kyrgyzstan
    0.94
    Activations Density 0.012%

    No Known Activations