© 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. 33014
    Prev
    Next
    INDEX
    Explanations

    Turkic, numbers, "The present"

    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
     Jamaica
    -0.85
    andola
    -0.80
    ätzt
    -0.79
    israel
    -0.77
     Colombia
    -0.77
     soğ
    -0.76
     Kenya
    -0.75
    🔐
    -0.72
     Moshe
    -0.72
     Catalan
    -0.71
    POSITIVE LOGITS
     Turkmenistan
    1.66
    Turk
    1.20
     тур
    1.14
     Turk
    1.12
    ý
    1.05
    Тур
    0.97
     Merv
    0.93
    тур
    0.89
     Neutr
    0.86
     Тур
    0.85
    Activations Density 0.015%

    No Known Activations