© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3508
    Prev
    Next
    INDEX
    Explanations

    real estate development projects

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ásticas
    -0.74
     ICI
    -0.69
     gắn
    -0.68
    하고
    -0.67
    الصفحه
    -0.66
     pakistan
    -0.66
     Tant
    -0.65
     ARP
    -0.65
     Conception
    -0.64
     सकती
    -0.64
    POSITIVE LOGITS
     development
    4.16
     developments
    3.20
    development
    3.17
    Development
    2.97
     DEVELOPMENT
    2.91
     desarrollo
    2.78
     Development
    2.75
     développement
    2.72
    DEVELOPMENT
    2.45
     Entwicklung
    2.44
    Activations Density 0.056%

    No Known Activations