© 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. 93666
    Prev
    Next
    INDEX
    Explanations

    jury and juror contexts

    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
     ''),
    -0.84
     Interpol
    -0.82
    宰
    -0.81
     Thessalon
    -0.79
     fiduci
    -0.79
     CMM
    -0.78
     claimant
    -0.78
     screenwriter
    -0.77
     CHAPTER
    -0.76
     Unsc
    -0.76
    POSITIVE LOGITS
     jurors
    2.94
     juror
    2.78
     jury
    2.69
     Jur
    2.52
    Jur
    2.42
    jur
    2.13
    jury
    1.89
     Jury
    1.87
     voir
    1.70
    Jury
    1.65
    Activations Density 0.051%

    No Known Activations