© 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. 1765
    Prev
    Next
    INDEX
    Explanations

    em names and company names

    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
     ,‬
    -2.88
     мои
    -2.44
    *}[
    -2.42
     theaters
    -2.41
    怎样的
    -2.36
    犼
    -2.31
     tillgäng
    -2.30
    几人
    -2.28
     lidí
    -2.25
    性价比
    -2.25
    POSITIVE LOGITS
    一個
    2.88
    r
    2.64
    芣
    2.59
    In
    2.47
    During
    2.42
    As
    2.41
    他們
    2.33
     简介
    2.33
    Leírás
    2.31
    0
    2.31
    Activations Density 0.001%

    No Known Activations