© 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. 11006
    Prev
    Next
    INDEX
    Explanations

    numbers and separators

    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
    athed
    -1.39
     nový
    -1.31
     Ofrece
    -1.28
     miest
    -1.21
    ejemplo
    -1.17
    qxd
    -1.13
     mueble
    -1.13
    ٦
    -1.13
     regalos
    -1.13
    Вот
    -1.13
    POSITIVE LOGITS
     its
    1.48
     spokesperson
    1.13
     and
    1.11
     کوت
    1.02
    انتهای
    1.02
     is
    1.02
    www
    1.01
    0
    0.94
    其
    0.93
     or
    0.91
    Activations Density 0.001%

    No Known Activations