© 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. 93953
    Prev
    Next
    INDEX
    Explanations

    packing and luggage

    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
     masked
    -0.88
    ꒪
    -0.87
    hardt
    -0.87
    Շ
    -0.84
     tractor
    -0.82
     customer
    -0.82
    fcntl
    -0.82
    筝
    -0.82
     خانگی
    -0.81
    érc
    -0.81
    POSITIVE LOGITS
     packing
    1.84
     Packing
    1.67
    Packing
    1.61
    packing
    1.59
     packers
    1.44
     luggage
    1.35
     travel
    1.32
    Pack
    1.30
     PACK
    1.27
     pack
    1.26
    Activations Density 0.027%

    No Known Activations