© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33448
    Prev
    Next
    INDEX
    Explanations

    universities after prepositions

    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
    Medica
    -0.91
    广州
    -0.88
    BufferException
    -0.85
    جوايز
    -0.85
    Ň
    -0.83
    íze
    -0.81
     neut
    -0.80
     ז
    -0.80
    Winnipeg
    -0.80
     قطاع
    -0.78
    POSITIVE LOGITS
     Harvard
    3.77
     Yale
    3.48
     Princeton
    3.06
     Stanford
    3.00
    Harvard
    2.95
    Yale
    2.95
     MIT
    2.66
    Princeton
    2.48
    Stanford
    2.45
     Dartmouth
    2.33
    Activations Density 0.178%

    No Known Activations