© 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. 39736
    Prev
    Next
    INDEX
    Explanations

    Buenos Aires, Rio de Janeiro

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

    The neuron strongly activates on mentions of major South American city names—most prominently “Buenos Aires.”

    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
    1
    -4.41
    0
    -3.59
    \
    -3.53
    p
    -3.42
    >
    -3.30
    6
    -3.25
    4
    -3.13
    5
    -3.02
    3
    -2.98
    9
    -2.86
    POSITIVE LOGITS
    訛
    2.53
    tać
    2.48
    
    2.45
    攫
    2.44
     když
    2.39
    琵琶
    2.36
     TÉCNICA
    2.34
    籐
    2.33
    拮
    2.33
    穢
    2.33
    Activations Density 0.004%

    No Known Activations