© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57850
    Prev
    Next
    INDEX
    Explanations

    labor and burden

    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
    preprocess
    -0.79
     preprocess
    -0.75
    ட்டி
    -0.74
    το
    -0.74
     activated
    -0.73
     corpo
    -0.73
    nimo
    -0.73
     fisio
    -0.71
    oną
    -0.71
     tanti
    -0.70
    POSITIVE LOGITS
     yoke
    1.17
     burden
    1.00
     Refresh
    0.94
    勞
    0.91
     burdens
    0.90
     easy
    0.88
    Refreshing
    0.85
     load
    0.85
     beban
    0.84
     LABOR
    0.84
    Activations Density 0.007%

    No Known Activations