© 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. 107652
    Prev
    Next
    INDEX
    Explanations

    oil spill events

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

    content related to oil spills, including mentions of cleanup, response, environmental impact, and related disasters like Deepwater Horizon.

    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
    -0.83
     IDA
    -0.75
    高等学校
    -0.75
    sniper
    -0.74
    的水
    -0.72
    Kura
    -0.72
    żeli
    -0.71
    Matériau
    -0.71
     Gild
    -0.71
    ఏ
    -0.71
    POSITIVE LOGITS
     oil
    2.58
    oil
    2.11
     Oil
    2.08
    Oil
    1.96
     oiled
    1.91
     spill
    1.75
     OIL
    1.63
    OIL
    1.55
     oils
    1.51
     oily
    1.45
    Activations Density 0.049%

    No Known Activations