© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68452
    Prev
    Next
    INDEX
    Explanations

    sulfur and oil content

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

    terms related to petroleum products and fossil fuels, particularly focusing on oil, sulfur, and fuel derivatives.

    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
    ᵥ
    -1.29
                               
    -1.20
     stronie
    -1.19
     mockery
    -1.16
                                
    -1.15
    ederen
    -1.14
     heridas
    -1.13
                             
    -1.11
    atação
    -1.11
                                 
    -1.10
    POSITIVE LOGITS
     oil
    1.45
     upwards
    1.19
    加以
    1.12
    加上
    1.12
    INCENT
    1.11
     dictate
    1.10
    九月
    1.09
    入手
    1.09
    Hvem
    1.07
     such
    1.06
    Activations Density 0.048%

    No Known Activations