© 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. 75635
    Prev
    Next
    INDEX
    Explanations

    online auctions and collectibles

    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
    Olvid
    -1.19
    你
    -1.10
    衬衫
    -1.10
    ometers
    -1.07
    ∽
    -1.06
     fortfarande
    -1.05
     сайта
    -1.05
     utensi
    -1.03
     يعني
    -1.02
     branca
    -1.01
    POSITIVE LOGITS
     but
    1.58
     that
    1.41
     respiración
    1.21
     frequenza
    1.13
     moment
    1.13
     this
    1.13
     rồi
    1.12
     luck
    1.11
     exist
    1.11
     way
    1.11
    Activations Density 0.049%

    No Known Activations