© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64423
    Prev
    Next
    INDEX
    Explanations

    box-sizing and box-shadow

    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
    زيون
    -0.81
     settler
    -0.78
     fattori
    -0.77
    üyor
    -0.75
    utebol
    -0.75
     INFORMACIÓN
    -0.75
     wyja
    -0.73
    canestro
    -0.72
     菓子
    -0.71
     workmen
    -0.71
    POSITIVE LOGITS
     Box
    1.34
     box
    1.29
    shadow
    1.25
    Box
    1.25
     BOX
    1.19
     Shadow
    1.10
     sizing
    1.10
     Boxes
    1.05
     boxes
    1.05
    BOX
    1.01
    Activations Density 0.014%

    No Known Activations