© 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. 118263
    Prev
    Next
    INDEX
    Explanations

    handmade crafts and artisans

    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
     farmacia
    -0.94
    pharm
    -0.91
    لاثة
    -0.90
    uclear
    -0.86
     pama
    -0.85
     vada
    -0.84
    penes
    -0.84
    炼
    -0.84
     gambling
    -0.83
     parati
    -0.83
    POSITIVE LOGITS
     crafts
    1.95
     craft
    1.74
     artisans
    1.71
     handic
    1.71
     handmade
    1.67
     handicrafts
    1.48
    crafts
    1.45
     Handic
    1.44
     artisan
    1.43
     Crafts
    1.40
    Activations Density 0.022%

    No Known Activations