© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 1349
    Prev
    Next
    INDEX
    Explanations

    marine and sea

    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_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
    ى
    0.55
    á
    0.53
    .,
    0.52
    ymce
    0.51
    encia
    0.51
    ides
    0.50
    ного
    0.50
    iled
    0.48
     수원
    0.48
    拢
    0.47
    POSITIVE LOGITS
     marine
    1.04
     sea
    1.02
     maritime
    1.02
     ocean
    1.01
     boat
    0.92
     deniz
    0.92
     seafood
    0.92
     sailors
    0.91
     seawater
    0.90
     sharks
    0.86
    Activations Density 0.449%

    No Known Activations