© 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. 8577
    Prev
    Next
    INDEX
    Explanations

    previewing content

    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
    瓩
    -3.36
    ↵↵
    -3.36
    ),
    -2.91
    H
    -2.86
     \&
    -2.72
    ↵
    -2.55
     Antrags
    -2.50
    se
    -2.48
    та
    -2.41
     ehemaligen
    -2.41
    POSITIVE LOGITS
    苼
    3.91
    阄
    3.41
    部分は
    3.30
    脔
    3.13
    囖
    3.09
    寕
    3.08
    臜
    3.00
    螄
    2.94
    時間も
    2.94
    禵
    2.92
    Activations Density 0.003%

    No Known Activations