© 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. 94114
    Prev
    Next
    INDEX
    Explanations

    summary and summarization

    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
     digs
    -0.72
     Bong
    -0.70
     Missed
    -0.65
     nghe
    -0.64
    Term
    -0.64
     correos
    -0.63
     Benjam
    -0.63
     ephe
    -0.63
     hunger
    -0.62
    Pand
    -0.61
    POSITIVE LOGITS
     summary
    1.56
     Summary
    1.44
    summary
    1.31
     summar
    1.23
    Summary
    1.21
     summaries
    1.21
    SUMMARY
    1.10
     SUMMARY
    1.10
     summarize
    1.09
     Abstra
    1.02
    Activations Density 0.010%

    No Known Activations