© 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. 57661
    Prev
    Next
    INDEX
    Explanations

    U.S. Dollars

    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
    潆
    -3.27
    鹋
    -3.08
    蟜
    -3.03
    1
    -2.77
    蹀
    -2.56
     klokken
    -2.47
    っていう
    -2.45
     ferien
    -2.39
    
    -2.38
    @[+][
    -2.34
    POSITIVE LOGITS
    $
    3.13
    咔嚓
    2.53
    讴
    2.34
    取り組み
    2.22
    𓋼
    2.17
    because
    2.17
    塤
    2.17
     Роб
    2.11
    鹛
    2.11
    听到了
    2.08
    Activations Density 0.003%

    No Known Activations