© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112783
    Prev
    Next
    INDEX
    Explanations

    capital city names

    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_10/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
    </h3>
    -2.03
    {
    -2.02
    </i>
    -1.98
    转换成
    -1.71
     imprescin
    -1.70
    но
    -1.68
    ඞ
    -1.67
     übri
    -1.66
     großzü
    -1.63
    libft
    -1.62
    POSITIVE LOGITS
    縯
    2.48
    莼
    2.45
    鋱
    2.31
    簟
    2.11
     expérimentés
    1.98
    蛧
    1.97
    henswürdigkeiten
    1.92
    𐐪
    1.89
    ತ್
    1.88
    銩
    1.84
    Activations Density 0.008%

    No Known Activations