Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8340
    Prev
    Next
    INDEX
    Explanations

    Utah places

    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
    Not in Any Lists

    No Comments

    Negative Logits
    JComboBox
    -0.74
     require
    -0.71
     Oviedo
    -0.71
     Dorset
    -0.71
     informaciones
    -0.70
    TTT
    -0.68
    ibia
    -0.68
    rowData
    -0.66
    PageInfo
    -0.66
     try
    -0.66
    POSITIVE LOGITS
     Ogden
    1.25
     Weber
    0.96
    Weber
    0.84
     restores
    0.76
     Харь
    0.76
     Northern
    0.75
     Od
    0.74
     banjir
    0.73
    Og
    0.73
     Huntsville
    0.71
    Activations Density 0.023%

    No Known Activations