© 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. 80871
    Prev
    Next
    INDEX
    Explanations

    legal judgments and findings

    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
     court
    -1.33
     Court
    -1.13
    court
    -0.94
     courts
    -0.93
     ihre
    -0.91
    法院
    -0.90
     вместе
    -0.88
     用
    -0.84
        
    -0.84
    чий
    -0.84
    POSITIVE LOGITS
    nargs
    1.19
     pakan
    1.09
     всички
    1.09
     itself
    1.03
     sano
    1.00
     puo
    0.99
     it
    0.99
    Partial
    0.98
     honneur
    0.98
    Other
    0.98
    Activations Density 0.046%

    No Known Activations