© 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. 22-GEMMASCOPE-RES-131K
    7. 28155
    Prev
    Next
    INDEX
    Explanations

    technical or scientific documentation

    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
    вую
    -1.08
     Использу
    -1.05
    тря
    -1.02
     there
    -1.00
     osal
    -0.98
    reiben
    -0.98
     também
    -0.98
    dür
    -0.97
    ají
    -0.97
     mikina
    -0.96
    POSITIVE LOGITS
    Passe
    1.02
    <eos>
    1.02
    Neder
    0.99
    之心
    0.98
     위해
    0.97
     упражнения
    0.96
    が
    0.95
    ./
    0.94
     mo
    0.94
     diss
    0.94
    Activations Density 0.000%

    No Known Activations