© 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. 22-GEMMASCOPE-RES-131K
    7. 130780
    Prev
    Next
    INDEX
    Explanations

    i2c, spi, and wire protocols

    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_22/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
    ’
    -1.93
     químicas
    -1.47
    要是
    -1.30
     baratas
    -1.29
     indivíduo
    -1.27
    ⫹
    -1.25
    就
    -1.25
     TMPro
    -1.24
    也是
    -1.24
     για
    -1.23
    POSITIVE LOGITS
    e
    1.26
     paraly
    1.23
     βρί
    1.22
    atella
    1.21
    PROTOCOL
    1.20
    对待
    1.14
    थ
    1.10
    chitz
    1.09
     stunts
    1.09
    ร์
    1.08
    Activations Density 0.012%

    No Known Activations