© 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. 47610
    Prev
    Next
    INDEX
    Explanations

    years and numbers

    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
    .
    -2.44
     Sábado
    -2.38
    
    -2.31
     Título
    -2.30
     Temporada
    -2.28
    鰾
    -2.23
    翾
    -2.20
    縯
    -2.17
     Políticas
    -2.05
     Publicado
    -2.05
    POSITIVE LOGITS
    s
    2.56
     \_
    2.50
    8
    2.42
    おかげ
    2.31
    愎
    2.30
    。」
    2.25
    \_
    2.20
     `
    2.20
                    
    2.19
     â
    2.19
    Activations Density 0.148%

    No Known Activations