© 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. 99811
    Prev
    Next
    INDEX
    Explanations

    people in service roles

    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
    publik
    -0.90
    fotograf
    -0.90
     SUPPORT
    -0.86
     ADVIS
    -0.85
    mmings
    -0.85
     États
    -0.84
    SUPPORT
    -0.83
    Bulb
    -0.81
     támogat
    -0.80
    ==>
    -0.79
    POSITIVE LOGITS
     responsible
    1.37
     service
    1.01
     reception
    0.94
     dedicated
    0.94
    的工作
    0.92
     staff
    0.91
     Responsible
    0.91
     enthusiastic
    0.89
     manager
    0.88
    Responsible
    0.88
    Activations Density 0.010%

    No Known Activations