© 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. 19237
    Prev
    Next
    INDEX
    Explanations

    requires us to adopt

    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
     but
    -1.74
    Ṁ
    -1.55
     its
    -1.41
     biß
    -1.31
     increíbles
    -1.30
     atraves
    -1.29
     suoi
    -1.27
     gutes
    -1.27
     espectaculares
    -1.27
    ḿ
    -1.26
    POSITIVE LOGITS
     most
    1.41
     affari
    1.34
    そして
    1.34
     έχουν
    1.29
     червня
    1.26
    нала
    1.24
     наиболее
    1.24
    ’，
    1.23
    זה
    1.23
    原始内容
    1.20
    Activations Density 0.059%

    No Known Activations