© 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. 41867
    Prev
    Next
    INDEX
    Explanations

    fully equipped kitchens

    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
     wydaj
    -1.23
    كثر
    -1.20
     objectively
    -1.20
    Več
    -1.17
     yıll
    -1.16
    につき
    -1.16
    という感じ
    -1.16
     arbeta
    -1.15
    管家
    -1.15
     amount
    -1.15
    POSITIVE LOGITS
     distintos
    1.32
     sekarang
    1.32
     verschillende
    1.31
     allerlei
    1.29
     Oost
    1.26
     Selasa
    1.25
    lampen
    1.23
    
    1.23
    — 
    1.23
    eload
    1.23
    Activations Density 0.055%

    No Known Activations