© 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. 12198
    Prev
    Next
    INDEX
    Explanations

    news headlines and sources

    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
     such
    -0.84
    aturan
    -0.81
     ervan
    -0.78
     Ge
    -0.77
     Han
    -0.77
     pre
    -0.76
     antes
    -0.75
     Har
    -0.75
    вера
    -0.75
     Pre
    -0.73
    POSITIVE LOGITS
     newspaper
    1.70
     news
    1.48
     newspapers
    1.32
     Newspaper
    1.23
     correspondent
    1.20
    news
    1.16
    online
    1.12
     correspondents
    1.10
    ην
    1.09
     BREAKING
    1.09
    Activations Density 0.029%

    No Known Activations