© 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. 22-GEMMASCOPE-RES-131K
    7. 38270
    Prev
    Next
    INDEX
    Explanations

    code structure and keywords

    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_22/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
     Perubahan
    -1.02
    ılıyor
    -0.97
    addRow
    -0.96
     amorosa
    -0.95
     Hingga
    -0.94
    ambah
    -0.90
    getSystemService
    -0.90
     osz
    -0.89
    лю
    -0.87
    Gründe
    -0.87
    POSITIVE LOGITS
     caballeros
    1.05
    ᴴ
    0.97
     splendor
    0.94
    橚
    0.91
    
    0.91
     dieren
    0.90
    渡し
    0.90
    льга
    0.89
     reizen
    0.89
     materialen
    0.88
    Activations Density 0.076%

    No Known Activations