© 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-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 9753
    Prev
    Next
    INDEX
    Explanations

    Sweden and Swedish cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     egregious
    0.52
     judicious
    0.45
    flavor
    0.43
     leveraging
    0.41
     wastes
    0.40
     neurologic
    0.40
    %
    0.40
     payoffs
    0.40
     bigotry
    0.39
    basketball
    0.38
    POSITIVE LOGITS
     Swedish
    1.47
     Gothenburg
    1.42
    Swedish
    1.41
     Å
    1.28
     Sweden
    1.27
     Uppsala
    1.25
     Göteborg
    1.24
     সুইড
    1.22
     Stockholm
    1.14
    Sweden
    1.14
    Activations Density 0.024%

    No Known Activations