© 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. 25715
    Prev
    Next
    INDEX
    Explanations

    shelf and shelf life

    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
     tutela
    -0.84
    ficha
    -0.84
    מן
    -0.83
    윤
    -0.81
    都沒
    -0.81
     ettei
    -0.80
    habitude
    -0.80
     bushel
    -0.79
     Flüs
    -0.77
    osha
    -0.76
    POSITIVE LOGITS
     shelf
    1.67
    shelf
    1.34
     shelves
    1.26
     shelving
    1.26
     Shelf
    1.24
    Shelf
    1.23
     brackets
    1.20
     display
    1.18
    helf
    1.07
     displaying
    0.98
    Activations Density 0.024%

    No Known Activations