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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 54261
    Prev
    Next
    INDEX
    Explanations

    exercise rights or authority

    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
     Endocrine
    -0.80
    kof
    -0.73
     brioche
    -0.71
     candidature
    -0.68
    importe
    -0.68
    訟
    -0.68
    atuor
    -0.66
    семь
    -0.66
     Incorporated
    -0.65
     Polaris
    -0.65
    POSITIVE LOGITS
     exercise
    7.03
    exercise
    6.00
     exercised
    5.81
     exercising
    5.72
     Exercise
    5.59
    Exercise
    5.44
     exercises
    5.06
     Exer
    4.56
    exer
    4.53
     EXERCISE
    4.47
    Activations Density 0.089%

    No Known Activations