© 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. 75194
    Prev
    Next
    INDEX
    Explanations

    sports events and achievements

    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
    ↵
    -1.42
     principalmente
    -1.34
     And
    -1.34
     gesamten
    -1.27
     alluminio
    -1.21
     about
    -1.20
     verbreitet
    -1.17
     kuhusu
    -1.16
    u
    -1.15
    de
    -1.14
    POSITIVE LOGITS
    although
    1.27
    endwhile
    1.26
    Menschen
    1.26
    炻
    1.24
    Waga
    1.23
    direkt
    1.21
    closedir
    1.20
    쑹
    1.16
    dokument
    1.16
    除非
    1.16
    Activations Density 0.039%

    No Known Activations