© 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. 73492
    Prev
    Next
    INDEX
    Explanations

    search and titles

    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
    客房
    -0.82
    álně
    -0.75
    委托
    -0.74
     здесь
    -0.69
    казания
    -0.69
     Sne
    -0.68
     Perth
    -0.68
    Spa
    -0.68
    labeled
    -0.66
    rean
    -0.66
    POSITIVE LOGITS
     searches
    1.38
     search
    1.27
     searched
    1.22
     Searches
    1.17
    search
    1.14
    searching
    1.05
    搜索
    1.02
     searching
    1.01
     Search
    0.98
    earch
    0.98
    Activations Density 0.007%

    No Known Activations