© 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. 56757
    Prev
    Next
    INDEX
    Explanations

    Jackson ObjectMapper

    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
     buckling
    -0.92
     Burden
    -0.92
     weighed
    -0.91
     under
    -0.90
     buckle
    -0.88
     sag
    -0.88
    Buck
    -0.86
     BUCK
    -0.86
     Buckle
    -0.86
     weighted
    -0.85
    POSITIVE LOGITS
     mapper
    1.20
     ObjectMapper
    1.07
    Mapper
    1.07
    mapper
    1.05
     Jackson
    0.95
    ObjectMapper
    0.95
    fasterxml
    0.93
     JACKSON
    0.81
     MAP
    0.81
     jackson
    0.80
    Activations Density 0.030%

    No Known Activations