© 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. 98817
    Prev
    Next
    INDEX
    Explanations

    making crafts

    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
     Schrauben
    -0.87
     nuov
    -0.86
    hugs
    -0.81
     âges
    -0.79
     disques
    -0.78
     картинки
    -0.78
     adesi
    -0.77
    瘆
    -0.76
     Gratis
    -0.75
     Pesticides
    -0.75
    POSITIVE LOGITS
     crochet
    1.94
     crafts
    1.86
     croche
    1.84
     painting
    1.81
     knitting
    1.77
     needle
    1.69
     knit
    1.66
     embroidery
    1.65
     craft
    1.62
     DIY
    1.55
    Activations Density 0.111%

    No Known Activations