© 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. 12022
    Prev
    Next
    INDEX
    Explanations

    parity conjecture

    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
    ыз
    -1.57
     København
    -1.55
     Internasional
    -1.55
    ଵ
    -1.54
     Ә
    -1.52
     Bildschirm
    -1.49
     Arquivado
    -1.41
    bunifu
    -1.41
    ଶ
    -1.40
    comber
    -1.39
    POSITIVE LOGITS
    ഃ
    1.52
    ÈNE
    1.40
     tenho
    1.40
    美味しいです
    1.39
     soluzioni
    1.36
     udang
    1.28
    𝔲
    1.28
    Nasc
    1.28
    慙
    1.27
    臯
    1.23
    Activations Density 0.065%

    No Known Activations