© 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. 104818
    Prev
    Next
    INDEX
    Explanations

    birds

    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
    ↵
    -2.53
    ☫
    -2.48
    呖
    -2.42
    s
    -2.38
    ing
    -2.28
     широкий
    -2.22
    d
    -2.19
    缡
    -2.14
    倏
    -2.14
     draped
    -2.13
    POSITIVE LOGITS
     Their
    2.89
    是
    2.69
    焿
    2.56
    嚒
    2.52
     offizielle
    2.50
     They
    2.48
     ถ้า
    2.48
     如果
    2.41
    </i>
    2.39
     údaje
    2.36
    Activations Density 0.007%

    No Known Activations