© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 184631
    Prev
    Next
    INDEX
    Explanations

    Chapter, spouses, introduction

    np_acts-logits-general · gemini-2.5-flash-lite

    Bubble Blowing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Phòng
    0.50
     பட்ட
    0.50
     جنگ
    0.49
     gewüns
    0.49
     등
    0.48
    なども
    0.48
    리
    0.48
    desPort
    0.48
     slučaj
    0.47
     Đông
    0.46
    POSITIVE LOGITS
    it
    0.61
    a
    0.58
    of
    0.55
    i
    0.54
    ika
    0.49
    et
    0.49
    Seat
    0.49
    arag
    0.47
    NJ
    0.47
    ok
    0.46
    Activations Density 0.001%

    No Known Activations