© 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. 10130
    Prev
    Next
    INDEX
    Explanations

    Gur words

    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
    ↵
    -3.20
    e
    -3.08
    a
    -2.77
    嗩
    -2.53
    Ⲉ
    -2.48
    氿
    -2.39
    鸲
    -2.34
    (
    -2.31
    ing
    -2.27
    蛱
    -2.23
    POSITIVE LOGITS
     雑貨
    2.61
    дәбият
    2.58
    經濟
    2.58
    鬭
    2.52
    Berdasarkan
    2.48
    Adapun
    2.48
    Menurutnya
    2.44
    
    2.42
    Each
    2.42
    最後
    2.39
    Activations Density 0.005%

    No Known Activations