© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38566
    Prev
    Next
    INDEX
    Explanations

    mipmap, lod, occasional, questions

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

    This neuron activates on references to mipmapping or level‐of‐detail settings (e.g. “mip,” “map,” “lod,” etc.) in code or texture metadata.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     to
    -1.95
     There
    -1.89
    ↵↵
    -1.82
     in
    -1.72
     with
    -1.69
    㐂
    -1.69
     noodzake
    -1.66
     provides
    -1.62
     mocht
    -1.62
     zwanzig
    -1.61
    POSITIVE LOGITS
    僰
    1.84
     grosse
    1.73
     другого
    1.72
    其他的
    1.70
     mesaj
    1.68
     parfü
    1.67
     baumwolle
    1.66
     magnifique
    1.63
     unab
    1.63
     etap
    1.62
    Activations Density 0.007%

    No Known Activations