© 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. 98802
    Prev
    Next
    INDEX
    Explanations

    SQL code, data, numbers, dates

    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
     September
    -0.97
     provide
    -0.93
     remain
    -0.88
     zaradi
    -0.87
     incentive
    -0.83
    董事长
    -0.83
     procedures
    -0.82
     tett
    -0.81
     masculina
    -0.80
     because
    -0.79
    POSITIVE LOGITS
     vorbereitet
    0.96
    aucun
    0.95
     lijkt
    0.90
     verrà
    0.89
    análisis
    0.88
     vooral
    0.87
    Notice
    0.86
    似乎
    0.86
    EMAN
    0.85
     vijf
    0.83
    Activations Density 0.078%

    No Known Activations