© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7624
    Prev
    Next
    INDEX
    Explanations

    Sikivu Hutchinson, SSA, Erica Chenoweth, Helvetica Neue, Fukushima Unit, MMP

    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
    的呢
    -2.39
    的吧
    -2.38
    闿
    -2.36
    泠
    -2.34
    玏
    -2.31
     октя
    -2.30
     initWithFrame
    -2.27
     approximate
    -2.25
    ковых
    -2.19
     about
    -2.14
    POSITIVE LOGITS
    是
    2.81
    也
    2.75
    o
    2.55
    )
    2.45
    」，
    2.45
    r
    2.41
    要
    2.38
                  
    2.31
    。”
    2.22
     笔画
    2.19
    Activations Density 0.011%

    No Known Activations