© 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. 70284
    Prev
    Next
    INDEX
    Explanations

    exterior design and styling

    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
    ज्ञान
    -0.97
    phòng
    -0.95
    bước
    -0.89
    iasis
    -0.89
    дые
    -0.88
    Auswahl
    -0.85
    ponym
    -0.85
    ್ರ
    -0.85
    dây
    -0.84
     slika
    -0.84
    POSITIVE LOGITS
     design
    1.51
     exterior
    1.34
     silhouette
    1.30
     styling
    1.21
     дизай
    1.20
     look
    1.16
     angular
    1.15
     designers
    1.11
     sleek
    1.10
     looks
    1.09
    Activations Density 0.043%

    No Known Activations