© 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. 22-GEMMASCOPE-RES-131K
    7. 39583
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Throughout
    -1.33
     has
    -1.27
     pelan
    -1.18
    Throughout
    -1.17
     throughout
    -1.09
     With
    -1.07
    There
    -1.00
     their
    -1.00
    After
    -0.97
     示例
    -0.95
    POSITIVE LOGITS
    <bos>
    1.37
    ʹ
    1.13
    璟
    1.11
     macetas
    1.05
    
    1.05
    ‒
    1.03
     áng
    1.02
    
    1.02
    Ꭾ
    1.02
    κα
    1.02
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.