© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79719
    Prev
    Next
    INDEX
    Explanations

    auxiliary or preposition followed

    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
     очень
    -1.21
     имеет
    -1.12
    omio
    -1.03
     certaines
    -1.01
    某些
    -1.00
     obecnie
    -0.99
     insbesondere
    -0.98
     certain
    -0.97
     tendrán
    -0.96
     mostrarán
    -0.96
    POSITIVE LOGITS
     also
    2.86
     similarly
    2.17
     another
    2.11
     likewise
    1.95
     ebenfalls
    1.83
     similar
    1.81
     then
    1.76
    อีก
    1.76
     également
    1.74
     también
    1.71
    Activations Density 0.094%

    No Known Activations