© 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. 72899
    Prev
    Next
    INDEX
    Explanations

    annual events and competitions

    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
     zmieni
    -1.54
     protože
    -1.51
    nému
    -1.45
    Océ
    -1.41
     takže
    -1.36
     znaczy
    -1.36
    的相关
    -1.35
     pestaña
    -1.34
     Unterrichts
    -1.33
     znale
    -1.32
    POSITIVE LOGITS
     falsa
    1.34
     <",
    1.33
     annually
    1.32
     atmosfera
    1.27
     devoirs
    1.27
    еру
    1.23
    MultipartFile
    1.23
    ваете
    1.23
    奶油
    1.23
     vanille
    1.22
    Activations Density 0.196%

    No Known Activations