© 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. 40-GEMMASCOPE-2-RES-262K
    7. 4198
    Prev
    Next
    INDEX
    Explanations

    underwater marine life

    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_40_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
    陇
    0.61
    垡
    0.59
    椃
    0.59
     árvore
    0.58
    秫
    0.55
    崞
    0.55
    虢
    0.54
    砀
    0.54
    农村
    0.54
    枌
    0.53
    POSITIVE LOGITS
     underwater
    2.19
     marine
    2.14
     ocean
    1.96
     seabed
    1.94
     seawater
    1.88
     undersea
    1.85
     oceanic
    1.80
     Underwater
    1.76
     reef
    1.68
    海底
    1.68
    Activations Density 0.101%

    No Known Activations