© 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. 29004
    Prev
    Next
    INDEX
    Explanations

    application layout structure

    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
     because
    -1.92
     anoche
    -1.54
     muchísimo
    -1.54
     This
    -1.49
     graças
    -1.46
     econô
    -1.46
     amenaz
    -1.45
     PUEDE
    -1.45
     vistazo
    -1.38
     direta
    -1.38
    POSITIVE LOGITS
     ‘
    1.49
    一個
    1.47
    这些
    1.47
     oscu
    1.37
    如
    1.34
    這些
    1.34
    POLIT
    1.34
     différente
    1.33
    >
    1.32
     этих
    1.32
    Activations Density 0.031%

    No Known Activations