© 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. 78554
    Prev
    Next
    INDEX
    Explanations

    identification of job-related information

    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
    균
    -0.76
    luan
    -0.75
    готови
    -0.73
    factura
    -0.73
    ダメージ
    -0.73
    idé
    -0.72
    ']));
    -0.71
    ⓐ
    -0.70
    modus
    -0.70
    lectoral
    -0.69
    POSITIVE LOGITS
    Employee
    1.10
     Employee
    1.02
     employee
    0.99
    employee
    0.95
    Job
    0.82
    シンプル
    0.81
     satis
    0.80
     McGregor
    0.80
     теории
    0.79
    Autor
    0.79
    Activations Density 0.011%

    No Known Activations