© 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. 31-GEMMASCOPE-2-RES-262K
    7. 43286
    Prev
    Next
    INDEX
    Explanations

    city names followed by sports teams

    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_31_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
    潙
    0.47
     Университе
    0.47
     почти
    0.46
     Реги
    0.46
     Grenze
    0.46
     Харків
    0.46
    б
    0.46
    mittag
    0.45
     Санкт
    0.44
    शेद
    0.44
    POSITIVE LOGITS
    MA
    0.44
    ;
    0.44
     anime
    0.42
    0.41
    umar
    0.40
     A
    0.40
    A
    0.40
    <strong>
    0.39
    .
    0.39
    《
    0.38
    Activations Density 0.002%

    No Known Activations