© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91676
    Prev
    Next
    INDEX
    Explanations

    checking expectations

    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
     which
    -1.00
     atque
    -0.88
     jusqu
    -0.84
    IfExists
    -0.84
     and
    -0.84
    同样
    -0.83
     tqdm
    -0.82
     souvent
    -0.81
    JUD
    -0.81
     is
    -0.79
    POSITIVE LOGITS
     expected
    1.52
    expected
    1.24
     expectations
    1.16
     expect
    1.09
     expectation
    1.03
     esperado
    1.03
     Expected
    1.02
    assertEquals
    1.01
    呶
    1.00
    预期
    0.97
    Activations Density 0.003%

    No Known Activations