© 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. 83181
    Prev
    Next
    INDEX
    Explanations

    news organizations reporting

    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
    Says
    -0.92
    祖国
    -0.84
     säger
    -0.81
     وقال
    -0.80
     bekijken
    -0.79
    ulur
    -0.78
     говорили
    -0.77
     kegiatan
    -0.76
    france
    -0.75
    jawab
    -0.75
    POSITIVE LOGITS
     reported
    4.28
     reports
    3.27
     reporting
    3.20
     report
    3.17
    reported
    2.94
    report
    2.58
    reports
    2.58
     Reported
    2.44
     REPORT
    2.41
    REPORT
    2.41
    Activations Density 0.036%

    No Known Activations