© 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. 74023
    Prev
    Next
    INDEX
    Explanations

    html form elements and classes

    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
    </h2>
    -2.25
     will
    -1.83
     be
    -1.68
        
    -1.62
     zowel
    -1.49
    i
    -1.45
    </h1>
    -1.44
     欣赏
    -1.42
      
    -1.41
            
    -1.41
    POSITIVE LOGITS
    樣子
    1.72
    鏡頭
    1.61
     samfun
    1.54
     praktische
    1.48
     swojej
    1.45
     gedachten
    1.45
    er
    1.45
     tailles
    1.43
     Mijn
    1.42
     Gebruik
    1.42
    Activations Density 0.003%

    No Known Activations