© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 47564
    Prev
    Next
    INDEX
    Explanations

    // +build tags

    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
    rrrrrrrr
    -1.73
    🙋
    -1.72
    ✌️
    -1.67
    🐾
    -1.64
     if
    -1.63
    !}
    -1.54
    🌟
    -1.52
    "};
    -1.51
     årene
    -1.50
    💞
    -1.50
    POSITIVE LOGITS
    的模样
    1.48
    都已经
    1.46
     which
    1.46
    Enfer
    1.43
    haustible
    1.35
    を紹介します
    1.34
     垃圾
    1.34
    後來
    1.34
     conforma
    1.32
    旁邊
    1.32
    Activations Density 0.004%

    No Known Activations