© 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. 23681
    Prev
    Next
    INDEX
    Explanations

    projection screen

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

    the neuron is sensitive to terms related to projecting or displaying images onto a surface.

    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
    тим
    -0.84
     hObject
    -0.83
    請繼續往下閱讀
    -0.82
    GRAPHICAL
    -0.82
    رارة
    -0.80
    пьютер
    -0.77
    ้น
    -0.76
     aussehen
    -0.76
     encontrarse
    -0.75
     overcrow
    -0.75
    POSITIVE LOGITS
     screen
    1.27
     projection
    1.05
     screens
    1.03
     Screen
    1.02
     viewing
    1.01
     ALR
    0.98
    スクリーン
    0.97
     tension
    0.96
     Screens
    0.88
    幕
    0.88
    Activations Density 0.015%

    No Known Activations