© 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. 34-GEMMASCOPE-RES-131K
    7. 83222
    Prev
    Next
    INDEX
    Explanations

    processing data or tasks

    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_34/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
    t
    -1.14
     questionSearch
    -1.09
     asistir
    -1.09
    ’
    -1.09
     controversy
    -1.06
     firs
    -1.00
    </strong>
    -1.00
     производится
    -0.99
     
    -0.98
     ingeniería
    -0.98
    POSITIVE LOGITS
     processing
    2.03
     Processing
    2.02
    processing
    1.93
    Processing
    1.84
     PROCESSING
    1.59
    PROCESSING
    1.50
     处理
    1.48
     обработки
    1.44
    處理
    1.39
    处理
    1.38
    Activations Density 0.029%

    No Known Activations