© 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. 16627
    Prev
    Next
    INDEX
    Explanations

    test conditions, skip logic

    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
     række
    -1.05
    ℛ
    -1.02
     >:
    -1.02
     katt
    -0.99
    😻
    -0.97
     Secretario
    -0.97
    []=
    -0.95
    🐾
    -0.95
     pemikiran
    -0.93
    😨
    -0.93
    POSITIVE LOGITS
     test
    1.27
     testing
    1.20
     เพราะ
    1.14
    因为
    1.14
    测试
    1.11
    ถึง
    1.11
     but
    1.10
    ಂದು
    1.09
     guaranteed
    1.02
     tests
    1.00
    Activations Density 0.026%

    No Known Activations