© 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. 6322
    Prev
    Next
    INDEX
    Explanations

    beyond safety limits

    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
    そして
    0.53
    inflammation
    0.46
    日々
    0.44
     импе
    0.43
     испы
    0.42
     auspices
    0.41
    婦
    0.41
     جميعا
    0.40
     তারপরে
    0.40
    两大
    0.39
    POSITIVE LOGITS
     deaktiv
    0.51
     موبائل
    0.49
     nieuwe
    0.47
     bırak
    0.45
     bảo
    0.44
    ۔
    0.43
    Digital
    0.43
     maximale
    0.43
     ekstrem
    0.43
     digitale
    0.43
    Activations Density 0.002%

    No Known Activations