© 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. 111977
    Prev
    Next
    INDEX
    Explanations

    Champs-Élysées and Capitoline Hill

    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
     frem
    0.46
    ഌ
    0.45
    ุ
    0.45
    اند
    0.44
    ع
    0.44
     torne
    0.44
     edific
    0.43
     gars
    0.43
    وبر
    0.43
    لع
    0.42
    POSITIVE LOGITS
    ————
    0.45
     কারণ
    0.44
     (=
    0.44
     방
    0.43
     사고
    0.43
     weren
    0.41
     മേ
    0.41
     ما
    0.41
     তুলনায়
    0.41
     (“
    0.40
    Activations Density 0.004%

    No Known Activations