© 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. 130957
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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
    certainly
    -1.91
     télécommande
    -1.88
    抨
    -1.87
     gier
    -1.79
    either
    -1.73
     diverses
    -1.73
     CERTAIN
    -1.73
    truly
    -1.73
    almost
    -1.70
     bijna
    -1.69
    POSITIVE LOGITS
    raujo
    1.87
     one
    1.80
    Etimología
    1.73
     красивый
    1.69
        
    1.64
    彿
    1.56
    oquia
    1.51
    metheus
    1.51
    १
    1.51
    льной
    1.49
    Activations Density 0.030%

    No Known Activations