© 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. 31479
    Prev
    Next
    INDEX
    Explanations

    3D printing files and designs

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Mosa
    -0.91
     auc
    -0.79
     KBS
    -0.77
    弼
    -0.75
    zenden
    -0.75
    lıyor
    -0.75
    KBS
    -0.73
     酷
    -0.73
     Xp
    -0.73
    Ǫ
    -0.72
    POSITIVE LOGITS
     STL
    2.48
     CAD
    2.44
    STL
    2.16
     stl
    2.08
    stl
    2.02
    CAD
    1.97
     printed
    1.61
     files
    1.55
     print
    1.50
     printable
    1.50
    Activations Density 0.038%

    No Known Activations