© 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. 10-GEMMASCOPE-RES-131K
    7. 19174
    Prev
    Next
    INDEX
    Explanations

    proper nouns and places

    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
    鹉
    -3.31
    嗵
    -3.03
    圌
    -2.92
    铩
    -2.63
     夜景
    -2.63
     北市
    -2.63
    茕
    -2.59
     ガイド
    -2.59
    我们是
    -2.56
     高清
    -2.53
    POSITIVE LOGITS
     
    3.59
     “
    3.06
     Currently
    3.03
     Also
    3.03
     Meanwhile
    2.98
     Slightly
    2.94
     Previously
    2.80
     Ideally
    2.78
    (
    2.73
     Personally
    2.69
    Activations Density 0.026%

    No Known Activations