© 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. 42352
    Prev
    Next
    INDEX
    Explanations

    margin css android xml

    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
    真的好
    -1.42
     içerisinde
    -1.41
    Fär
    -1.33
    这两个
    -1.26
     égale
    -1.25
    hebung
    -1.24
     financieras
    -1.24
    Ejemplos
    -1.23
    これが
    -1.22
    就很
    -1.22
    POSITIVE LOGITS
     how
    1.42
    __':
    
    1.32
     all
    1.31
    }_{
    1.30
    Aiheesta
    1.26
     II
    1.23
     why
    1.22
    AppCompatTheme
    1.22
    чик
    1.22
    чки
    1.20
    Activations Density 1.034%

    No Known Activations