© 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. 43582
    Prev
    Next
    INDEX
    Explanations

    east west north south

    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
    葑
    -2.11
     Він
    -2.06
     four
    -1.92
    でしたが
    -1.88
    沨
    -1.87
    いわ
    -1.86
    もや
    -1.84
     one
    -1.83
     sizable
    -1.80
     two
    -1.80
    POSITIVE LOGITS
    most
    2.69
    逦
    2.69
    3
    2.39
     impromptu
    2.20
    鸝
    2.19
     embellished
    2.17
    </h1>
    2.16
     apresenta
    2.11
     acclaimed
    2.11
    </h5>
    2.08
    Activations Density 0.019%

    No Known Activations