© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75323
    Prev
    Next
    INDEX
    Explanations

    outsourcing and offshore services

    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_22/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
     tanques
    -1.30
     paznok
    -1.23
    บน
    -1.17
     administrar
    -1.16
     erinner
    -1.16
     giorni
    -1.16
    putExtra
    -1.15
    ὴν
    -1.14
     fragte
    -1.13
     empêche
    -1.13
    POSITIVE LOGITS
     for
    1.29
     countries
    1.27
     China
    1.15
     global
    1.12
     cheaper
    1.10
    וּ
    1.09
     outsourcing
    1.09
     Asia
    1.06
     location
    1.05
     European
    1.05
    Activations Density 0.033%

    No Known Activations