© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33724
    Prev
    Next
    INDEX
    Explanations

    creativity and innovation

    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
     Milestone
    -0.93
     התח
    -0.91
     sélections
    -0.85
     آرز
    -0.84
     Eko
    -0.84
     餐厅
    -0.82
    chose
    -0.82
     kue
    -0.81
     disques
    -0.81
    GBP
    -0.81
    POSITIVE LOGITS
     creativity
    3.48
     creative
    3.17
     Creativity
    2.86
    Creativity
    2.66
     innovation
    2.50
     Creative
    2.39
    creative
    2.27
     твор
    2.17
     Innovation
    2.14
    Creative
    2.13
    Activations Density 0.045%

    No Known Activations