© 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. 69155
    Prev
    Next
    INDEX
    Explanations

    creating code constructs

    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
     then
    -2.42
     
    -2.38
    を中心
    -2.36
     culmin
    -2.22
     accentu
    -2.17
    屃
    -2.17
    卝
    -2.13
    蟥
    -2.03
    鲞
    -2.03
     dubbed
    -2.02
    POSITIVE LOGITS
    ſelves
    2.50
     exquisite
    2.38
    瀦
    2.30
     impeccable
    2.28
     Some
    2.27
     शुर
    2.25
     összefoglaló
    2.23
     Eight
    2.19
     Numerous
    2.17
    Воспита
    2.17
    Activations Density 0.017%

    No Known Activations