© 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. 49464
    Prev
    Next
    INDEX
    Explanations

    printing documents and jobs

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

    The neuron detects terms describing printing device operations—especially verbs and nouns like “print,” “scan,” “copy,” and “produce” in printer/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
    Gew
    -0.93
     أبريل
    -0.82
    vulas
    -0.82
     dy
    -0.76
    âu
    -0.76
     \|
    -0.74
     DISPLAY
    -0.73
    nachweise
    -0.73
    jspx
    -0.73
     pigment
    -0.72
    POSITIVE LOGITS
     pages
    1.03
     Quality
    0.96
     jobs
    0.94
     job
    0.94
     printed
    0.90
    มาณ
    0.89
     documents
    0.88
     quality
    0.84
     test
    0.81
    鏡
    0.80
    Activations Density 0.048%

    No Known Activations