© 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. 75220
    Prev
    Next
    INDEX
    Explanations

    code structure or comments

    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
     Democrá
    -1.37
    bahaya
    -1.35
     (
    -1.34
    in
    -1.32
    zeiti
    -1.30
    iyle
    -1.23
     becomes
    -1.22
     during
    -1.20
    ساب
    -1.20
    桿
    -1.18
    POSITIVE LOGITS
    阅读原文
    1.46
    ########.
    1.42
     palav
    1.40
     توضی
    1.37
     succinct
    1.37
    GIUM
    1.33
    点此
    1.32
    谖
    1.30
    ＊＊＊＊
    1.30
     tapete
    1.29
    Activations Density 0.189%

    No Known Activations