© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58200
    Prev
    Next
    INDEX
    Explanations

    freshwater, brackish water

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

    references to aquatic environments like waters, rivers, oceans, and shorelines.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    水中
    -1.23
    Aquatic
    -1.21
     Underwater
    -1.20
     Aquatic
    -1.17
     waterproof
    -1.17
     AGUA
    -1.15
     aquatic
    -1.13
     underwater
    -1.12
     WATER
    -1.10
     Waterproof
    -1.10
    POSITIVE LOGITS
     rivers
    2.09
     river
    2.02
     lake
    1.91
     Lake
    1.84
     lakes
    1.80
    Lake
    1.64
     Rivers
    1.60
    rivers
    1.55
     River
    1.53
    river
    1.46
    Activations Density 0.051%

    No Known Activations