© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 4661
    Prev
    Next
    INDEX
    Explanations

    North Korea missile launches

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ینو
    0.67
    𝐦
    0.66
    ваме
    0.61
    ین
    0.59
    ερμαν
    0.59
    𝗺
    0.58
    ্ট
    0.55
     दट
    0.55
    َم
    0.55
    т
    0.55
    POSITIVE LOGITS
     .
    0.67
     l
    0.59
     citadel
    0.58
     cigarette
    0.57
     kimchi
    0.57
     Pyongyang
    0.55
    ach
    0.54
     cartridge
    0.54
    韓国
    0.54
    }.
    0.54
    Activations Density 0.001%

    No Known Activations