© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116673
    Prev
    Next
    INDEX
    Explanations

    oil and gas development

    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
    bilden
    -0.84
    Dons
    -0.81
     AVAILABLE
    -0.81
    kozás
    -0.77
    passen
    -0.77
    ætte
    -0.76
    grunn
    -0.74
    ובת
    -0.73
     dangere
    -0.73
     Destruction
    -0.73
    POSITIVE LOGITS
     development
    2.25
    development
    1.72
    Development
    1.69
     Development
    1.61
     DEVELOPMENT
    1.48
    开发
    1.37
     developmental
    1.36
     develop
    1.36
     développement
    1.36
     desarrollo
    1.25
    Activations Density 0.047%

    No Known Activations