© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 35838
    Prev
    Next
    INDEX
    Explanations

    Trafalgar Square and financial institutions

    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_40_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
     bottomRight
    0.44
     Consumer
    0.43
     subsid
    0.40
     Kne
    0.40
     Consumers
    0.40
    alui
    0.39
     setDefault
    0.38
    卧
    0.38
     settle
    0.38
    的长
    0.38
    POSITIVE LOGITS
    paris
    0.41
     panneau
    0.40
     ক্যাপ্টেন
    0.40
    Japan
    0.40
    ಮೆ
    0.40
    ヨーロッパ
    0.39
    Pren
    0.39
    ificação
    0.39
    гів
    0.39
    дент
    0.38
    Activations Density 0.003%

    No Known Activations