© 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. 60208
    Prev
    Next
    INDEX
    Explanations

    final report or case report

    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
     մ
    -0.75
     demonio
    -0.72
    录制
    -0.71
    حيات
    -0.71
    recorded
    -0.70
     jedną
    -0.69
     echar
    -0.68
     Jesucristo
    -0.66
     Lund
    -0.66
     рассмотре
    -0.65
    POSITIVE LOGITS
     report
    5.81
     reports
    4.88
    report
    4.22
     Report
    4.09
    Report
    4.03
    reports
    3.53
     Reports
    3.50
    REPORT
    3.47
    报告
    3.44
     REPORT
    3.42
    Activations Density 0.133%

    No Known Activations