© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34508
    Prev
    Next
    INDEX
    Explanations

    data and parameters

    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
     pauvreté
    -1.27
     later
    -1.22
     posteriormente
    -1.16
     subsequent
    -1.14
     anderen
    -1.10
     später
    -1.10
     любого
    -1.08
     autorytatywna
    -1.07
    ">(</
    -1.07
    ઃ
    -1.05
    POSITIVE LOGITS
    视着
    1.13
     рассказывает
    1.04
    ført
    1.03
     includes
    1.00
     financières
    0.98
     påvir
    0.98
    主要是
    0.97
     häm
    0.97
    atürk
    0.94
    othermal
    0.93
    Activations Density 0.002%

    No Known Activations