© 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. 59305
    Prev
    Next
    INDEX
    Explanations

    booking services, rooms, and appointments

    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
    
    -1.01
    🫢
    -0.98
     alcool
    -0.96
     cioc
    -0.94
    🆕
    -0.94
     oportunidade
    -0.92
     gero
    -0.92
     alimentare
    -0.91
     cardiovas
    -0.91
     bestem
    -0.91
    POSITIVE LOGITS
     through
    1.47
     tickets
    1.40
     online
    1.31
     a
    1.28
     seats
    1.26
    Through
    1.16
     for
    1.16
     rooms
    1.09
     flights
    1.05
     appointments
    1.01
    Activations Density 0.011%

    No Known Activations