© 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. 79293
    Prev
    Next
    INDEX
    Explanations

    cpu cores and processors

    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
    łaści
    -0.78
    誼
    -0.75
    spania
    -0.75
    converters
    -0.74
    ypeł
    -0.73
    dsn
    -0.72
    太好了
    -0.70
    了他的
    -0.70
     leg
    -0.69
    ंदी
    -0.69
    POSITIVE LOGITS
     processor
    1.52
     processors
    1.23
    Processor
    1.18
     quad
    1.16
    processor
    1.10
     Processor
    1.07
    Quad
    1.00
     processing
    0.99
     проце
    0.98
     Processors
    0.96
    Activations Density 0.031%

    No Known Activations