© 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. 41-GEMMASCOPE-2-RES-262K
    7. 199
    Prev
    Next
    INDEX
    Explanations

    major 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_all/layer_41_width_262k_l0_big
    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
     discontinuities
    0.50
    )-\
    0.50
    ปลี่ยน
    0.49
    ະພັນ
    0.48
    รรม
    0.48
    ាល
    0.48
    ើយ
    0.47
     deformity
    0.47
    ាប
    0.47
     ـ
    0.47
    POSITIVE LOGITS
     London
    0.98
     Montreal
    0.93
     Paris
    0.92
     Chicago
    0.92
     Amsterdam
    0.92
     Budapest
    0.91
     Berlin
    0.89
     Madrid
    0.89
     Toronto
    0.88
     Seattle
    0.88
    Activations Density 0.012%

    No Known Activations