© 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. 107821
    Prev
    Next
    INDEX
    Explanations

    design and designers

    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
     rRNA
    -0.81
     paintings
    -0.76
     PHR
    -0.73
     polymerase
    -0.73
    mography
    -0.72
    SLS
    -0.72
     Terrestrial
    -0.72
    skb
    -0.71
     waiver
    -0.71
     Loan
    -0.70
    POSITIVE LOGITS
     design
    1.71
     designers
    1.69
    Design
    1.53
     designer
    1.53
     Designers
    1.52
     Design
    1.52
    design
    1.51
     дизайн
    1.44
     tasarım
    1.34
    设计
    1.34
    Activations Density 0.047%

    No Known Activations