© 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. 31840
    Prev
    Next
    INDEX
    Explanations

    manual or automatic transmissions

    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
     वा
    -0.66
    rotter
    -0.66
    ciale
    -0.64
    tadiene
    -0.63
     SwiftUI
    -0.63
    devServer
    -0.63
    じて
    -0.63
    Dimensions
    -0.62
    رأ
    -0.61
    irection
    -0.61
    POSITIVE LOGITS
     manual
    3.75
    manual
    3.16
     Manual
    3.02
    Manual
    2.94
     automatic
    2.91
     MANUAL
    2.69
    MANUAL
    2.58
    automatic
    2.50
    Automatic
    2.44
     Automatic
    2.42
    Activations Density 0.020%

    No Known Activations