© 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. 62570
    Prev
    Next
    INDEX
    Explanations

    digging and excavation

    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
     çar
    -0.76
    Kata
    -0.74
     diterapkan
    -0.74
    ğum
    -0.74
    Doors
    -0.73
    <<(
    -0.71
    ктория
    -0.71
    悟空
    -0.71
    itete
    -0.69
     Directory
    -0.69
    POSITIVE LOGITS
     digging
    4.28
     dug
    3.50
     digs
    3.39
     dig
    3.27
     excavation
    3.14
    Dig
    3.02
     digger
    3.00
     Dig
    2.92
     excavated
    2.67
    dig
    2.66
    Activations Density 0.040%

    No Known Activations