© 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. 13390
    Prev
    Next
    INDEX
    Explanations

    Command, forge, fml

    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
    。“
    -1.43
    쩡
    -1.37
    onaceous
    -1.37
     hará
    -1.36
    Étymologie
    -1.35
    ).”
    -1.34
     пр
    -1.29
    。”
    -1.28
     некоторые
    -1.25
     особо
    -1.25
    POSITIVE LOGITS
     betek
    1.48
     fahrrad
    1.42
     tamamen
    1.39
     flink
    1.39
     hunne
    1.39
     privacidade
    1.38
    桖
    1.38
     素描
    1.36
     auffi
    1.35
     經典
    1.35
    Activations Density 0.017%

    No Known Activations