© 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. 10-GEMMASCOPE-RES-131K
    7. 1063
    Prev
    Next
    INDEX
    Explanations

    universities and related locations

    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_10/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
    扨
    -2.20
     kapture
    -2.09
     konsumen
    -2.09
    gebraucht
    -2.08
     رائع
    -2.06
    䛗
    -2.05
    without
    -2.05
     特写
    -2.00
     wichtigste
    -1.98
    
    -1.95
    POSITIVE LOGITS
    呖
    2.13
     /
    1.99
    Он
    1.97
     &#
    1.94
     >
    1.83
     canadienne
    1.82
     от
    1.80
     obscene
    1.80
     не
    1.78
    隄
    1.74
    Activations Density 0.006%

    No Known Activations