© 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. 22-GEMMASCOPE-RES-131K
    7. 28428
    Prev
    Next
    INDEX
    Explanations

    merge and combine

    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_22/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
     plátano
    -0.89
     portero
    -0.81
     Marcus
    -0.80
     sky
    -0.75
     atún
    -0.75
     Handler
    -0.75
     spicy
    -0.74
    getCause
    -0.73
    uteur
    -0.73
    անո
    -0.73
    POSITIVE LOGITS
     merge
    1.55
     merging
    1.49
     merger
    1.43
     overlap
    1.38
    合并
    1.36
    Merge
    1.34
     merged
    1.34
     combined
    1.32
    merge
    1.26
     combining
    1.25
    Activations Density 0.093%

    No Known Activations