© 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. 10-GEMMASCOPE-RES-131K
    7. 84698
    Prev
    Next
    INDEX
    Explanations

    Barcelona

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

    The neuron strongly activates on occurrences of “Barcelona” (and related place names like Camp Nou), i.e. tokens naming the city or its landmarks.

    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
    ISHMENT
    -2.48
    潆
    -2.42
     Penggunaan
    -2.39
    CurtirCurtir
    -2.31
    
    -2.28
    纐
    -2.27
     deafening
    -2.25
    的
    -2.25
    لغة
    -2.25
     Using
    -2.25
    POSITIVE LOGITS
    .
    3.84
    蔸
    2.45
    镚
    2.38
     邸
    2.25
    who
    2.22
    槼
    2.19
    渽
    2.19
    []
    2.09
    which
    2.09
     reiter
    2.08
    Activations Density 0.003%

    No Known Activations