© 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. 22-GEMMASCOPE-RES-131K
    7. 32830
    Prev
    Next
    INDEX
    Explanations

    entity and its attributes

    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
    Negative Logits
    inawa
    -1.28
    therosclerosis
    -1.05
    РО
    -1.03
     of
    -1.02
     because
    -1.02
    действие
    -1.02
    сайт
    -1.00
     виру
    -0.97
    ilets
    -0.96
    ustes
    -0.96
    POSITIVE LOGITS
     related
    1.53
     attributes
    1.50
     tasks
    1.49
     necesit
    1.41
     features
    1.37
    related
    1.34
     elements
    1.34
     activities
    1.20
     items
    1.20
     functions
    1.18
    Activations Density 0.157%

    No Known Activations