© 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. 37723
    Prev
    Next
    INDEX
    Explanations

    opening of venues and businesses

    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
    usepackage
    -1.00
     gili
    -0.98
     padang
    -0.97
     ateliers
    -0.96
     じ
    -0.94
    Actividades
    -0.93
    urd
    -0.92
    izmu
    -0.91
     farmacia
    -0.90
     ulter
    -0.90
    POSITIVE LOGITS
     opening
    1.43
     concepto
    1.39
     location
    1.39
     opened
    1.36
     концеп
    1.28
     otev
    1.22
     concept
    1.21
     space
    1.19
     occupying
    1.16
    setLocation
    1.11
    Activations Density 0.068%

    No Known Activations