© 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. 56988
    Prev
    Next
    INDEX
    Explanations

    testing and mocking code

    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
     if
    -1.47
     or
    -1.41
     Perhaps
    -1.16
     seems
    -1.16
     allows
    -1.05
     perhaps
    -1.00
     which
    -0.99
     until
    -0.99
    Perhaps
    -0.98
     uses
    -0.96
    POSITIVE LOGITS
     test
    2.16
     mock
    2.13
     Test
    1.88
    mock
    1.85
     TEST
    1.83
    Test
    1.83
     тесто
    1.79
    test
    1.77
     Mock
    1.76
    Mock
    1.73
    Activations Density 0.049%

    No Known Activations