© 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. 130881
    Prev
    Next
    INDEX
    Explanations

    in [place name]

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

    The neuron flags prepositions like “in” and “at” when they introduce locational (or sometimes temporal) phrases, especially before place names.

    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
    different
    -1.90
    肫
    -1.81
    
    -1.66
    [])
    -1.58
    alties
    -1.58
    
    -1.58
    rophes
    -1.55
    Хьажоргаш
    -1.55
     sehe
    -1.54
    devtool
    -1.54
    POSITIVE LOGITS
    (
    1.78
        
    1.75
                
    1.73
           
    1.66
     However
    1.63
            
    1.59
     You
    1.57
     that
    1.55
     podrán
    1.55
     This
    1.54
    Activations Density 0.123%

    No Known Activations