© 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. 119826
    Prev
    Next
    INDEX
    Explanations

    foreign language apostrophes

    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
     these
    -1.77
     this
    -1.69
     Если
    -1.64
     Then
    -1.60
     iniciativas
    -1.58
     those
    -1.57
     subsequently
    -1.56
     alér
    -1.56
    しなかった
    -1.50
     concluye
    -1.50
    POSITIVE LOGITS
    =?,
    2.00
     baan
    1.88
     tien
    1.84
     fordi
    1.81
     eet
    1.78
     sommer
    1.77
     ordre
    1.76
     ons
    1.76
     tô
    1.73
     knop
    1.73
    Activations Density 1.225%

    No Known Activations