© 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. 19744
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
    0
    -3.41
    {
    -2.92
     one
    -2.81
     After
    -2.78
     When
    -2.75
    a
    -2.67
     an
    -2.61
     Before
    -2.53
     from
    -2.45
    -
    -2.45
    POSITIVE LOGITS
     tabak
    2.64
     kredi
    2.61
     interessante
    2.48
    苼
    2.44
     fotografie
    2.41
     ของ
    2.39
     goofy
    2.36
     estándares
    2.34
     ใน
    2.33
     置物
    2.33
    Activations Density 0.023%

    No Known Activations