© 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. 10-GEMMASCOPE-RES-131K
    7. 120146
    Prev
    Next
    INDEX
    Explanations

    housing and accommodation

    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_10/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
     撮っ
    -1.77
     menyen
    -1.71
     that
    -1.55
     politiet
    -1.55
    鄚
    -1.54
     Vergine
    -1.50
     们
    -1.45
     confirmar
    -1.45
     isang
    -1.45
    ụn
    -1.41
    POSITIVE LOGITS
     accomod
    1.71
    ↵↵↵
    1.33
    ↵↵↵↵↵↵↵↵↵
    1.32
                
    1.31
     sueño
    1.29
    .”
    1.29
     quirks
    1.29
     Provided
    1.28
    谅
    1.27
    .
    1.27
    Activations Density 0.024%

    No Known Activations