© 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. 72803
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    ou
    -1.52
     bardziej
    -1.40
     которое
    -1.34
     האם
    -1.34
    ซึ่ง
    -1.33
    回想
    -1.30
    𝟗
    -1.27
    西部
    -1.25
    сутствие
    -1.24
    ll
    -1.23
    POSITIVE LOGITS
     obicei
    1.60
    <bos>
    1.52
     of
    1.47
    pró
    1.41
    yttö
    1.30
    𝑿
    1.25
    produkter
    1.25
    在这里
    1.25
     new
    1.23
    quelize
    1.23
    Activations Density 0.005%

    No Known Activations