© 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. 76939
    Prev
    Next
    INDEX
    Explanations

    employer and future opportunity

    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
     MST
    -0.77
    kinin
    -0.75
    ∛
    -0.71
    Þ
    -0.71
     vect
    -0.71
    omor
    -0.71
    JECT
    -0.71
    converter
    -0.70
    AFTA
    -0.69
    WithContext
    -0.69
    POSITIVE LOGITS
     employers
    6.66
     employer
    6.59
    Employers
    4.97
    employer
    4.88
     Employers
    4.84
     Employer
    4.56
    Employer
    4.50
     Arbeitgeber
    3.72
     работо
    3.72
     EMPLOY
    3.53
    Activations Density 0.103%

    No Known Activations