© 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. 75286
    Prev
    Next
    INDEX
    Explanations

    discussing effects

    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
     saisons
    -1.81
     Produit
    -1.68
    奩
    -1.62
     dilaksanakan
    -1.59
     circulación
    -1.55
     parcs
    -1.53
     PÅ
    -1.48
     épo
    -1.47
     refuerzo
    -1.47
     livres
    -1.46
    POSITIVE LOGITS
     you
    2.05
     in
    1.89
     if
    1.85
    7
    1.70
     فيها
    1.59
     Again
    1.46
    5
    1.44
     I
    1.43
     breezy
    1.41
    SOLVED
    1.39
    Activations Density 0.095%

    No Known Activations