© 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. 10-GEMMASCOPE-RES-131K
    7. 69755
    Prev
    Next
    INDEX
    Explanations

    pulling or pulling out

    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_10/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
     neue
    -1.99
     increase
    -1.97
     unparalleled
    -1.90
     unrelenting
    -1.89
    ↵↵
    -1.89
     would
    -1.89
     besonders
    -1.87
     give
    -1.87
     will
    -1.86
     may
    -1.81
    POSITIVE LOGITS
    pulled
    2.44
    泚
    2.27
    盦
    2.25
    pull
    2.22
    蚡
    2.16
    </b>
    2.08
     célè
    2.06
    
    2.05
    屙
    2.05
     équipé
    2.05
    Activations Density 0.023%

    No Known Activations