© 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-65K
    7. 12032
    Prev
    Next
    INDEX
    Explanations

    sea and ocean concepts

    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_65k_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
    醪
    0.65
     Erfurt
    0.53
    馍
    0.53
    乡村
    0.48
    节日
    0.47
    许可
    0.47
     হ্যান
    0.47
    䒾
    0.47
     समझौते
    0.46
    陕西
    0.46
    POSITIVE LOGITS
     marine
    1.91
     ocean
    1.82
     maritime
    1.82
     seaf
    1.68
     coastal
    1.67
     seawater
    1.66
     seafood
    1.66
     nautical
    1.62
     oceanic
    1.61
     sea
    1.57
    Activations Density 0.297%

    No Known Activations