© 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. 10-GEMMASCOPE-RES-131K
    7. 57478
    Prev
    Next
    INDEX
    Explanations

    baggage, surcharge, UIApplication

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

    The main thing this neuron does is find mentions of baggage or luggage.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    鐃
    -2.53
    硨
    -2.48
    啣
    -2.30
    ཋ
    -2.28
    o
    -2.23
    ⸒
    -2.23
    a
    -2.13
    埽
    -2.13
    }$
    -2.11
     Which
    -2.09
    POSITIVE LOGITS
    
    2.41
    蹩
    2.25
     esche
    2.22
    嘞
    2.20
     baggage
    2.19
    って何
    2.19
    也知道
    2.16
     of
    2.16
     benötigt
    2.11
     în
    2.09
    Activations Density 0.001%

    No Known Activations