© 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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 64272
    Prev
    Next
    INDEX
    Explanations

    dwellings and workplaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     наших
    0.43
     खरीदारी
    0.43
    墩
    0.43
     челове
    0.42
     landfills
    0.41
     giants
    0.40
    క్క
    0.40
     뿌
    0.39
    ospitals
    0.39
     theatres
    0.39
    POSITIVE LOGITS
     في
    0.55
     in
    0.50
     casa
    0.49
     villa
    0.48
    ใน
    0.46
     în
    0.45
     residences
    0.45
    公寓
    0.44
     nella
    0.43
    cope
    0.42
    Activations Density 0.022%

    No Known Activations