© 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. 21777
    Prev
    Next
    INDEX
    Explanations

    programming code types

    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
    l
    -1.64
     美しい
    -1.50
    v
    -1.48
     aktivitet
    -1.43
     {,
    -1.41
    ᕱ
    -1.40
    n
    -1.39
    f
    -1.38
     those
    -1.37
     centímetros
    -1.36
    POSITIVE LOGITS
     ésta
    1.67
     Geheimnis
    1.49
     nuevos
    1.45
     otros
    1.37
     Unglück
    1.34
     Lernen
    1.33
    četně
    1.32
     ciertos
    1.31
    chait
    1.31
     p
    1.30
    Activations Density 0.002%

    No Known Activations