© 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. 10-GEMMASCOPE-RES-131K
    4. 70648
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     about
    -0.88
    taobao
    -0.87
     {
    
    
    -0.86
     خواهد
    -0.84
     kore
    -0.83
     ekos
    -0.83
    ujem
    -0.82
     lname
    -0.81
     even
    -0.81
    Beij
    -0.81
    POSITIVE LOGITS
     insolvent
    1.04
     belligerent
    0.98
     prosecutions
    0.94
     identifiers
    0.93
     '../../../../
    0.92
     idleness
    0.90
     держать
    0.90
    erokee
    0.89
     suicides
    0.88
    abello
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.