© 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. 58229
    Prev
    Next
    INDEX
    Explanations

    airbag inflation and deployment

    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
     THEOD
    -0.70
    URDAY
    -0.68
     perspectiva
    -0.67
     renovables
    -0.66
     succulent
    -0.65
    зами
    -0.65
     кало
    -0.65
     boots
    -0.64
     republiky
    -0.64
    ʺ
    -0.64
    POSITIVE LOGITS
     deployment
    1.48
     deploying
    1.37
     Deployment
    1.24
     deploy
    1.23
     inflater
    1.21
    Deployment
    1.17
    Deploy
    1.14
    Inflation
    1.14
     Deploy
    1.14
     deployments
    1.13
    Activations Density 0.016%

    No Known Activations