© 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. 127796
    Prev
    Next
    INDEX
    Explanations

    variable declarations or assignments

    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
     there
    -1.33
     each
    -1.20
     it
    -1.15
     this
    -1.00
     its
    -0.97
     bagian
    -0.96
    primitive
    -0.96
     who
    -0.93
     తె
    -0.92
    kadang
    -0.91
    POSITIVE LOGITS
    Beij
    1.12
    铑
    1.01
     cruisers
    1.00
    カク
    0.96
     nether
    0.96
    Zdrav
    0.95
     fondamental
    0.94
    Sedangkan
    0.94
    Теперь
    0.93
     wherefore
    0.93
    Activations Density 0.030%

    No Known Activations