© 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. 84593
    Prev
    Next
    INDEX
    Explanations

    year-over-year percentage changes

    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
     gradually
    -0.88
    当代
    -0.88
    今晚
    -0.83
     fisuras
    -0.83
     poprzez
    -0.82
     until
    -0.82
     затра
    -0.82
    pady
    -0.82
     cheerful
    -0.81
    باره
    -0.81
    POSITIVE LOGITS
     year
    2.36
     compared
    1.77
    year
    1.70
     год
    1.46
     Year
    1.33
    compared
    1.33
     año
    1.29
    Year
    1.23
     YEAR
    1.20
     compare
    1.18
    Activations Density 0.017%

    No Known Activations