© 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. 117135
    Prev
    Next
    INDEX
    Explanations

    reducing emissions and fuel consumption

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    loem
    -0.77
    Reward
    -0.75
     dú
    -0.75
     auff
    -0.75
    GLuint
    -0.73
    ッキ
    -0.73
    Leben
    -0.72
     punish
    -0.71
     BM
    -0.71
     judicial
    -0.71
    POSITIVE LOGITS
     greenhouse
    2.61
     emissions
    2.56
     carbon
    2.28
     emission
    2.27
     Greenhouse
    2.02
     GHG
    1.96
     Emission
    1.87
     Emissions
    1.86
     emitted
    1.76
     emits
    1.76
    Activations Density 0.030%

    No Known Activations