© 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. 47645
    Prev
    Next
    INDEX
    Explanations

    natural gas supply and use

    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
    Splash
    -0.81
    otonic
    -0.77
     Splash
    -0.76
    🇦
    -0.76
    openqa
    -0.76
     phosphatase
    -0.74
    hoka
    -0.72
     cacao
    -0.72
     DMSO
    -0.72
    电机
    -0.72
    POSITIVE LOGITS
     gas
    4.47
     Gas
    3.39
    Gas
    3.23
    gas
    3.23
     газо
    2.91
    ガス
    2.69
     GAS
    2.64
    GAS
    2.56
     LNG
    2.45
     gás
    2.22
    Activations Density 0.099%

    No Known Activations