© 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. 13495
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    Хороший
    -1.92
    кроссовки
    -1.78
    喼
    -1.77
    鄖
    -1.76
     malang
    -1.71
     بسیار
    -1.71
    ※※
    -1.69
     abiye
    -1.68
    Краси
    -1.66
    Хорошо
    -1.66
    POSITIVE LOGITS
    </em>
    2.25
     to
    2.19
     
    2.00
     (
    1.99
    .
    1.95
    </h2>
    1.85
    and
    1.85
    an
    1.84
    ,
    1.81
    ”
    1.79
    Activations Density 0.003%

    No Known Activations