© 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. 106785
    Prev
    Next
    INDEX
    Explanations

    unemployment rates

    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
    >−</
    -0.85
    ']))
    -0.84
     limitar
    -0.82
    atov
    -0.81
     introducir
    -0.81
    omento
    -0.81
    ↴
    -0.81
    indows
    -0.79
     Gebet
    -0.77
    Polyline
    -0.76
    POSITIVE LOGITS
     unemployment
    1.77
    Unemployment
    1.40
     Unemployment
    1.08
     rate
    1.06
     jobless
    1.03
     rates
    0.97
    率
    0.90
     percentages
    0.90
     ILO
    0.86
     taux
    0.84
    Activations Density 0.020%

    No Known Activations