© 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. 34-GEMMASCOPE-RES-131K
    7. 744
    Prev
    Next
    INDEX
    Explanations

    fellow countrymen, citizens, members

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     diferentes
    -1.00
     otros
    -0.96
     différentes
    -0.90
    の良い
    -0.90
     verschiedenen
    -0.88
     others
    -0.88
     différents
    -0.87
    姪
    -0.86
     praktisch
    -0.86
    艰难
    -0.85
    POSITIVE LOGITS
     countrymen
    1.37
     travelers
    1.24
     travellers
    1.23
     traveler
    1.11
     countryman
    1.10
     traveller
    1.09
     sufferers
    1.08
     citizens
    1.07
    shipping
    1.06
     classmates
    0.99
    Activations Density 0.011%

    No Known Activations