© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 98858
    Prev
    Next
    INDEX
    Explanations

    water bodies and aquatic life

    np_acts-logits-general · gemini-2.5-flash-lite

    ocean and sea properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getTransforms
    0.59
     Architectural
    0.58
    兕
    0.57
    过的
    0.55
     나무
    0.55
    崞
    0.55
    钎
    0.54
    郏
    0.54
    癣
    0.53
    嵘
    0.53
    POSITIVE LOGITS
     ocean
    0.98
     phytoplankton
    0.92
    oplankton
    0.89
     seawater
    0.80
    ocean
    0.78
    海洋
    0.77
     oceanic
    0.77
     jellyfish
    0.75
     benthic
    0.74
     cruises
    0.70
    Activations Density 0.070%

    No Known Activations