© 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. 10-GEMMASCOPE-RES-131K
    7. 67847
    Prev
    Next
    INDEX
    Explanations

    visuals, models, textures

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

    The neuron specializes in spotting technical graphics and rendering terms—words naming visual‐asset elements like textures, models, polygons, animations, UI, and related descriptors.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     to
    -1.83
     any
    -1.32
    囉
    -1.31
     three
    -1.27
     краї
    -1.24
     financieras
    -1.20
    ねば
    -1.18
     financieros
    -1.17
     one
    -1.16
     bisog
    -1.16
    POSITIVE LOGITS
     controversi
    1.20
    唻
    1.17
    колад
    1.16
     brasileira
    1.13
    thè
    1.13
     relev
    1.12
    сив
    1.12
     být
    1.11
    important
    1.09
     geschenk
    1.09
    Activations Density 0.034%

    No Known Activations