© 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. 92389
    Prev
    Next
    INDEX
    Explanations

    print and pattern

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron peaks on words describing printed designs—particularly “print”/“prints” and related terms in fabric or product descriptions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Sculpt
    -0.93
    énez
    -0.90
     javax
    -0.87
    糰
    -0.85
    ilstein
    -0.85
    Individual
    -0.83
     sculpture
    -0.83
     刺繍
    -0.82
     leather
    -0.82
     sculpting
    -0.82
    POSITIVE LOGITS
     print
    1.88
     prints
    1.67
     printed
    1.65
     pattern
    1.63
    柄
    1.48
     patterns
    1.45
    Printed
    1.43
     Printed
    1.41
     Print
    1.37
     printing
    1.30
    Activations Density 0.035%

    No Known Activations