© 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. 22-GEMMASCOPE-RES-131K
    7. 39886
    Prev
    Next
    INDEX
    Explanations

    Hurricanes, XML declarations

    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_22/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
     cristianos
    -1.29
     tuve
    -1.13
     parfüm
    -1.12
     dioses
    -1.09
    '=>$
    -1.09
     Projektu
    -1.08
     menciptakan
    -1.08
     lelaki
    -1.05
     ángeles
    -1.05
     perbuatan
    -1.05
    POSITIVE LOGITS
    2
    1.40
     udang
    1.17
    Eerste
    1.15
     diametro
    1.14
    داية
    1.14
    8
    1.13
     côtes
    1.09
     传统
    1.09
     civils
    1.07
    Mijn
    1.05
    Activations Density 0.001%

    No Known Activations