© 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. 31621
    Prev
    Next
    INDEX
    Explanations

    graduate student 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
    profession
    -0.77
     Acad
    -0.77
     voters
    -0.77
    🏎
    -0.76
    🚚
    -0.75
    ="#">
    -0.75
    ɥ
    -0.75
     élé
    -0.74
    邕
    -0.74
    ßen
    -0.73
    POSITIVE LOGITS
     graduate
    4.16
     doctoral
    2.92
     Graduate
    2.88
     grad
    2.86
    Graduate
    2.80
    graduate
    2.75
     PhD
    2.70
     postgraduate
    2.58
     student
    2.47
     postdoctoral
    2.41
    Activations Density 0.053%

    No Known Activations