© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27876
    Prev
    Next
    INDEX
    Explanations

    trip duration and activities

    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
     new
    -1.45
     product
    -1.35
     provide
    -1.28
     warung
    -1.27
     who
    -1.23
     provided
    -1.23
     produced
    -1.22
     newly
    -1.22
     generated
    -1.22
     creating
    -1.20
    POSITIVE LOGITS
    安排
    1.56
     návště
    1.48
     itinerary
    1.42
    ského
    1.34
    颌
    1.31
    licopter
    1.30
    
    1.28
     campeonato
    1.26
     sightseeing
    1.26
     spend
    1.25
    Activations Density 0.028%

    No Known Activations