© 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. 77195
    Prev
    Next
    INDEX
    Explanations

    engine cylinders and compression

    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
     Gore
    -0.91
    Validation
    -0.82
    
    -0.79
    querySelector
    -0.77
    accharide
    -0.75
    tolo
    -0.75
    ò
    -0.75
    aliyet
    -0.75
    vl
    -0.74
    Validate
    -0.74
    POSITIVE LOGITS
     compression
    1.56
    compression
    1.40
     Compression
    1.30
    Compression
    1.26
     cylinders
    1.13
     cylinder
    1.08
     cran
    1.04
     compresión
    1.02
     цилинд
    1.02
     decompression
    1.01
    Activations Density 0.009%

    No Known Activations