© 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-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2491
    Prev
    Next
    INDEX
    Explanations

    bag, luggage, suitcase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     దేవ
    0.98
     coronation
    0.93
    馗
    0.93
     Burnett
    0.89
     đua
    0.89
     Rex
    0.88
    昌
    0.88
     cauliflower
    0.86
    ๏
    0.86
    RPM
    0.86
    POSITIVE LOGITS
     bag
    3.01
     bags
    2.85
     handbag
    2.84
     luggage
    2.82
     Bags
    2.76
     backpacks
    2.74
     backpack
    2.64
    bag
    2.64
     suitcase
    2.58
     BAG
    2.58
    Activations Density 0.780%

    No Known Activations