© 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. 66755
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and punctuation

    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
    {
    -2.39
     -
    -2.08
     has
    -2.00
    镬
    -1.94
     После
    -1.84
    
    -1.79
     obecnie
    -1.74
    了一句
    -1.73
     violeta
    -1.72
    当即
    -1.72
    POSITIVE LOGITS
    would
    2.22
    /**
    1.95
     inauguración
    1.88
    퐿
    1.80
    我的
    1.77
    )
    1.73
    こんばん
    1.70
     بدون
    1.69
    être
    1.68
    lgari
    1.67
    Activations Density 0.007%

    No Known Activations