© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93764
    Prev
    Next
    INDEX
    Explanations

    printing

    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
    anadium
    -0.96
     sketching
    -0.90
     sketches
    -0.88
     světa
    -0.87
    enaire
    -0.84
    angulaire
    -0.82
    Documentation
    -0.81
    quisa
    -0.81
     sculpted
    -0.81
     inalámbrica
    -0.80
    POSITIVE LOGITS
     printing
    3.00
     print
    2.56
     printer
    2.55
     Printing
    2.55
     printers
    2.50
     Print
    2.20
    Printing
    2.17
     printed
    2.13
     Printer
    2.13
    printing
    2.09
    Activations Density 0.095%

    No Known Activations