© 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. 66606
    Prev
    Next
    INDEX
    Explanations

    column headers

    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
     bilen
    -0.96
    banken
    -0.94
     Sempre
    -0.91
    jarse
    -0.90
     BOUND
    -0.86
    口味
    -0.85
     Général
    -0.85
     olabilir
    -0.83
     Bacterial
    -0.83
     Certains
    -0.83
    POSITIVE LOGITS
     then
    1.48
    ediat
    0.96
     number
    0.95
    큼
    0.94
     количество
    0.92
     szeptember
    0.91
     потому
    0.89
     aproximado
    0.88
    uestamente
    0.88
    achte
    0.88
    Activations Density 0.003%

    No Known Activations