© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130631
    Prev
    Next
    INDEX
    Explanations

    calculating and determining mathematical problems

    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
     including
    -1.47
     and
    -1.45
     Fakten
    -1.33
    ximity
    -1.30
     then
    -1.27
    cenza
    -1.26
    \">\
    -1.23
    tifully
    -1.23
    のかも
    -1.17
    )):
    
    -1.16
    POSITIVE LOGITS
     autre
    1.55
    不一样
    1.48
     what
    1.45
    vestidos
    1.43
    Pozdrawiam
    1.36
    اغ
    1.36
    Hogyan
    1.32
    Manfaat
    1.30
    pozdrawiam
    1.29
    За
    1.27
    Activations Density 0.232%

    No Known Activations