© 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. 57591
    Prev
    Next
    INDEX
    Explanations

    "is" "are" "you" questions

    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
    ↵
    -1.31
     is
    -1.29
    との
    -1.24
     will
    -1.23
     desarrolló
    -1.22
     aveva
    -1.21
     astuces
    -1.20
    much
    -1.20
    と同じ
    -1.20
     here
    -1.16
    POSITIVE LOGITS
    ihnachts
    1.63
     hijas
    1.48
     pantallas
    1.48
     jeszcze
    1.44
    หน้าน
    1.40
     historias
    1.38
    rscheinlich
    1.37
     colecciones
    1.37
     poblaciones
    1.37
    ݿ
    1.30
    Activations Density 0.031%

    No Known Activations