© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 183253
    Prev
    Next
    INDEX
    Explanations

    3D fabrication and printing

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

    3D printing and additive manufacturing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Clap
    0.47
     peas
    0.43
    یشه
    0.43
     fries
    0.42
    SleepHours
    0.41
     Sá
    0.41
     clap
    0.40
    ʦ
    0.40
     sauce
    0.40
     Packet
    0.39
    POSITIVE LOGITS
     voxel
    0.72
    voxel
    0.64
     fabricating
    0.59
     निर्माण
    0.58
     fabrication
    0.55
    pixel
    0.52
     biom
    0.52
    oxel
    0.51
    konstru
    0.50
    constructing
    0.48
    Activations Density 0.054%

    No Known Activations