© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11183
    Prev
    Next
    INDEX
    Explanations

    Bulgarian and Bulgaria

    np_acts-logits-general · gemini-2.5-flash-lite

    Bulgarian and Sofia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     將
    0.56
    範圍
    0.53
    Ყ
    0.52
     因為
    0.51
    顯示
    0.51
    ździer
    0.51
     其中
    0.51
    轉
    0.51
    Ὑ
    0.51
    䋇
    0.50
    POSITIVE LOGITS
     Bulgarian
    1.91
     Bulgaria
    1.80
     българ
    1.74
     България
    1.59
     Bulgar
    1.40
     Sofia
    1.32
     Bulg
    1.29
    Sofia
    1.16
     пър
    1.06
    Bul
    1.05
    Activations Density 0.135%

    No Known Activations