© 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. 98515
    Prev
    Next
    INDEX
    Explanations

    Reuters news agency

    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
    zczegól
    -0.80
    BERRY
    -0.80
    CHAPTER
    -0.79
     reprendre
    -0.78
    𝐓
    -0.77
    vanou
    -0.76
    raged
    -0.75
    《
    -0.75
    ΑΛ
    -0.73
    chable
    -0.73
    POSITIVE LOGITS
     Reuters
    1.61
    REUTERS
    1.26
    reuters
    1.25
    Reuters
    1.05
     reporting
    1.01
     RE
    0.97
     Reporting
    0.87
    Katalog
    0.85
     Reuter
    0.83
    𝘫
    0.83
    Activations Density 0.029%

    No Known Activations