© 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. 90298
    Prev
    Next
    INDEX
    Explanations

    code snippets and keywords

    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
     besonderes
    -1.71
     erwähnten
    -1.70
     außerord
    -1.66
     sujeito
    -1.65
     Gebet
    -1.64
     Bewußt
    -1.63
     same
    -1.63
     Gefäng
    -1.59
     two
    -1.57
     cérebro
    -1.55
    POSITIVE LOGITS
     astr
    1.38
     entusias
    1.37
     müh
    1.34
    他的
    1.33
    ⌒
    1.31
     criter
    1.30
     byz
    1.30
     Telef
    1.29
    水彩
    1.29
    埼玉
    1.29
    Activations Density 0.031%

    No Known Activations