© 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. 11871
    Prev
    Next
    INDEX
    Explanations

    Il, Ile, Ir, Internazionale

    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
     ihre
    -2.91
     mittleren
    -2.48
    meteries
    -2.47
    阄
    -2.47
    ↵↵
    -2.36
    劻
    -2.33
    ᨁ
    -2.33
    ൨
    -2.31
    ्स
    -2.30
    家乡
    -2.27
    POSITIVE LOGITS
    {
    3.47
     auffi
    2.67
    桖
    2.55
     Then
    2.47
    大概
    2.42
    歘
    2.36
    
    2.34
    
    2.31
     and
    2.30
    ти
    2.30
    Activations Density 0.001%

    No Known Activations