© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34387
    Prev
    Next
    INDEX
    Explanations

    luggage, baggage, and belongings

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on words referring to luggage and related packing or baggage items.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     or
    -1.43
    re
    -1.15
    o
    -1.12
    }$,
    -1.09
    mitz
    -1.08
    How
    -1.06
            
    -1.05
     see
    -1.03
    ↵
    -1.02
    Our
    -1.02
    POSITIVE LOGITS
     luggage
    1.61
     maleta
    1.21
     basan
    1.20
    ᥬ
    1.20
     baggage
    1.19
     belongings
    1.17
     dvě
    1.15
    ívne
    1.14
    𐬹
    1.13
    
    1.13
    Activations Density 0.009%

    No Known Activations