© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 6800
    Prev
    Next
    INDEX
    Explanations

    box-shadow/text-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
     Industry
    -0.79
    ❰
    -0.77
    rú
    -0.77
    termo
    -0.76
    ラインナップ
    -0.75
     bait
    -0.74
     industry
    -0.74
    鍙
    -0.72
    روع
    -0.71
    ッズ
    -0.70
    POSITIVE LOGITS
    inset
    1.56
     inset
    1.54
    BoxShadow
    1.27
    Inset
    1.05
    boxShadow
    1.02
     box
    1.00
     Box
    0.87
     BOX
    0.86
    Shadow
    0.86
     Shadow
    0.85
    Activations Density 0.008%

    No Known Activations