© 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. 105974
    Prev
    Next
    INDEX
    Explanations

    Yuehua, Xinhua, Tsinghua

    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
    檍
    -2.92
    t
    -2.78
    ).
    -2.66
    т
    -2.61
     myſelf
    -2.58
    霂
    -2.39
    .”
    -2.27
     ());
    -2.25
     неё
    -2.23
     時尚
    -2.20
    POSITIVE LOGITS
    {
    2.81
     myriad
    2.45
                
    2.38
     zumal
    2.30
    ↵↵
    2.19
    跟著
    2.14
     gän
    2.13
    蚨
    2.13
    裡的
    2.11
    棡
    2.09
    Activations Density 0.002%

    No Known Activations