© 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. 76599
    Prev
    Next
    INDEX
    Explanations

    criminal justice and legal proceedings

    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
     Chilli
    -0.94
    спа
    -0.84
     lawsuits
    -0.81
     ۱۰
    -0.80
     Mutation
    -0.80
     artefacts
    -0.80
    èmes
    -0.77
     ieder
    -0.77
    =")
    -0.76
     lawsuit
    -0.76
    POSITIVE LOGITS
     trial
    1.26
     Crown
    1.25
     police
    1.10
     crown
    1.04
    Crown
    1.02
    Prosecutors
    1.01
     Criminal
    1.00
     jury
    0.95
    Trial
    0.94
     conviction
    0.93
    Activations Density 0.025%

    No Known Activations