© 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. 10-GEMMASCOPE-RES-131K
    4. 19509
    Prev
    Next
    INDEX
    Explanations

    surroundings

    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
    𓋼
    -2.75
     vya
    -2.55
     lancia
    -2.47
     bluse
    -2.44
     magasiner
    -2.42
     moulin
    -2.42
     voleva
    -2.41
     truk
    -2.39
    黢
    -2.38
     monstre
    -2.36
    POSITIVE LOGITS
    ↵↵
    3.61
     někter
    2.80
     are
    2.75
     surroundings
    2.56
     ubiquitous
    2.55
     
    2.50
     extremely
    2.47
     ample
    2.47
     whats
    2.38
    ikusbot
    2.38
    Activations Density 0.001%

    No Known Activations