© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 48250
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and code fragments

    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
     charmant
    -1.97
     ambassade
    -1.77
     ſte
    -1.66
     mystérie
    -1.63
    
    -1.59
     副本
    -1.59
     剑
    -1.59
     industrielle
    -1.58
     电脑
    -1.57
     soldat
    -1.57
    POSITIVE LOGITS
     sorgfäl
    1.78
     äusser
    1.77
     üblichen
    1.70
     There
    1.59
     wußte
    1.59
     praktischen
    1.52
    少しでも
    1.52
     because
    1.49
     valuable
    1.48
     can
    1.48
    Activations Density 0.007%

    No Known Activations