© 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. 220313
    Prev
    Next
    INDEX
    Explanations

    transitioning owner | Zombies | samples showed | of of | on behalf of | cooperation indicated | duly indicated | Usually Sp | Online Community

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

    technical classifications class Parallel insights upgrades

    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
     기준
    0.46
     শর্ত
    0.46
     می‌باشد
    0.45
     حر
    0.44
    기준
    0.44
    aryng
    0.43
    甭
    0.43
     سپس
    0.43
    чности
    0.42
     ዓይ
    0.42
    POSITIVE LOGITS
    0.54
    0.53
    E
    0.52
     Contributing
    0.50
     large
    0.48
    ：
    0.48
     crowded
    0.48
     Thanh
    0.48
     lớn
    0.47
    :
    0.47
    Activations Density 0.001%

    No Known Activations