© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103700
    Prev
    Next
    INDEX
    Explanations

    academic university 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
     वर्ग
    -0.82
    ueger
    -0.81
     districts
    -0.80
     Polri
    -0.76
     слой
    -0.75
     counties
    -0.75
     Erscheinung
    -0.75
    hematics
    -0.75
    מבר
    -0.74
    ilian
    -0.72
    POSITIVE LOGITS
     academic
    1.33
     Rector
    1.32
     Academic
    1.24
     Dean
    1.13
     campus
    1.09
     faculty
    1.03
     faculties
    1.02
    academic
    1.02
     Senate
    1.02
     university
    1.02
    Activations Density 0.013%

    No Known Activations