© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8253
    Prev
    Next
    INDEX
    Explanations

    ocean, marine life, and fishing

    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_16k_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
    崞
    0.61
    芨
    0.57
    秫
    0.56
    Soil
    0.54
    弇
    0.53
    徭
    0.53
    馍
    0.53
    Pyro
    0.52
    虢
    0.52
     Soils
    0.52
    POSITIVE LOGITS
     ocean
    1.70
     marine
    1.63
     seafood
    1.56
     oceanic
    1.55
    海洋
    1.48
     fish
    1.48
     seawater
    1.45
     fishing
    1.41
     oceans
    1.40
     fisheries
    1.40
    Activations Density 0.253%

    No Known Activations