© 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. 98366
    Prev
    Next
    INDEX
    Explanations

    degrees and limits

    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
    dür
    -1.28
    Xuất
    -1.22
    これは
    -1.17
    خخ
    -1.16
    ishments
    -1.12
     it
    -1.11
    Elő
    -1.10
     parlar
    -1.10
    gá
    -1.10
    issance
    -1.09
    POSITIVE LOGITS
     
    1.13
    為に
    1.09
    -
    1.04
     varies
    1.01
     obyvateľov
    1.00
     cilvē
    0.96
     finalmente
    0.95
     medzi
    0.95
     циф
    0.94
    bove
    0.94
    Activations Density 0.094%

    No Known Activations