© 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. 85595
    Prev
    Next
    INDEX
    Explanations

    Rio de Janeiro

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

    The neuron detects mentions of the Brazilian city “Rio de Janeiro.”

    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
    ).
    -2.97
    ↵↵
    -2.92
    .”
    -2.81
    ();
    -2.58
    }
    -2.58
    昻
    -2.45
    }{
    -2.44
    </tr>
    -2.41
    癩
    -2.41
    lossians
    -2.39
    POSITIVE LOGITS
    硨
    3.31
    
    3.05
     dein
    2.52
    ﯼ
    2.50
    ㍉
    2.47
    旆
    2.45
    
    2.45
    鹛
    2.44
    Ꮈ
    2.39
    龉
    2.39
    Activations Density 0.003%

    No Known Activations