© 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. 10-GEMMASCOPE-RES-131K
    7. 119482
    Prev
    Next
    INDEX
    Explanations

    words starting with cu

    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_10/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
    .
    -2.94
    ”.
    -2.69
    .“
    -2.66
    瀦
    -2.64
    ↵↵
    -2.53
    O
    -2.48
    但
    -2.48
    pertino
    -2.47
    我们
    -2.42
     })
    -2.39
    POSITIVE LOGITS
     "
    3.02
     waren
    2.64
    向了
    2.56
     was
    2.47
    koszulka
    2.42
    y
    2.36
     escucha
    2.36
     cette
    2.34
     gerçekten
    2.34
    篡
    2.33
    Activations Density 0.013%

    No Known Activations