© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2108
    Prev
    Next
    INDEX
    Explanations

    stereo vision, depth, 3D

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

    The neuron specializes in spotting technical academic writing marked by numbers and numeric references—e.g. citation brackets, measurement values or section numbers—alongside domain‐specific terms in scholarly papers.

    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
    凯
    -0.80
    DNA
    -0.78
     Kruse
    -0.77
    LECTION
    -0.77
    topLeft
    -0.74
    Barcode
    -0.73
    центр
    -0.72
     quer
    -0.72
    лиза
    -0.71
    poti
    -0.71
    POSITIVE LOGITS
     disparity
    1.36
     disparities
    1.23
     depth
    1.09
     Stereo
    1.00
     stereo
    0.98
     Depth
    0.97
    Census
    0.94
    Stereo
    0.93
    depth
    0.86
     Census
    0.85
    Activations Density 0.025%

    No Known Activations