© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 103126
    Prev
    Next
    INDEX
    Explanations

    oil spills and prevention

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

    the word "spill" in various contexts, especially related to oil spills and liquid accidents.

    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_10/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
    </b>
    -2.86
     {
    -2.80
     o
    -2.67
    A
    -2.67
     «
    -2.64
    an
    -2.64
     do
    -2.63
    </td>
    -2.61
    '
    -2.56
    \
    -2.50
    POSITIVE LOGITS
    </strong>
    3.78
    ’,
    3.11
    </h3>
    2.86
    pulseira
    2.67
    鬭
    2.66
    鈇
    2.63
     daban
    2.58
     mélang
    2.55
    продам
    2.50
    ucap
    2.50
    Activations Density 0.001%

    No Known Activations