© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66478
    Prev
    Next
    INDEX
    Explanations

    multi-lingual greetings and phrases

    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
    ୌ
    -2.23
    ,'
    -1.95
     آن‌ها
    -1.91
    肫
    -1.87
    Răsp
    -1.81
    However
    -1.80
     proporcionar
    -1.78
     são
    -1.78
    ၞ
    -1.77
    ,"
    -1.73
    POSITIVE LOGITS
     sebagainya
    1.88
    );
    1.83
    </h1>
    1.70
    Ｐ
    1.48
    .
    1.47
    😇
    1.47
    tya
    1.45
     hah
    1.44
     ★★★★
    1.44
    contributions
    1.42
    Activations Density 0.001%

    No Known Activations