© 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. 824
    Prev
    Next
    INDEX
    Explanations

    car trims and models

    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
    おわりに
    -1.59
    へ行
    -1.55
    余談
    -1.52
    まさかの
    -1.48
    次回は
    -1.45
    Conclusie
    -1.41
    つづく
    -1.36
     the
    -1.36
    {
    -1.35
    もう少し
    -1.34
    POSITIVE LOGITS
     imaginación
    1.47
    hogy
    1.47
    *{\
    1.45
    นี้
    1.37
     rhino
    1.34
    拗
    1.33
    ीय
    1.33
     podle
    1.32
    Santé
    1.31
     มี
    1.30
    Activations Density 0.025%

    No Known Activations