© 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. 34688
    Prev
    Next
    INDEX
    Explanations

    3D media projection

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

    The neuron detects mentions of three-dimensional (3D) content, spotting tokens like “dimensional,” “(,” “3,” and “D” that signify 3D.

    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
     vời
    -0.78
    TWA
    -0.76
    ȧ
    -0.75
     nimble
    -0.74
     main
    -0.73
    цио
    -0.71
     statutory
    -0.71
    док
    -0.70
    🌫
    -0.70
    ַּ
    -0.69
    POSITIVE LOGITS
     IMAX
    1.48
     theaters
    1.23
     stere
    1.17
     theater
    1.10
     projection
    1.06
    convertTo
    1.06
    converted
    1.05
     Stereo
    0.99
     immersive
    0.99
     glasses
    0.98
    Activations Density 0.023%

    No Known Activations