© 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. 70469
    Prev
    Next
    INDEX
    Explanations

    C++ include statements

    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
     with
    -1.80
     a
    -1.71
    銪
    -1.53
     ‘
    -1.48
    一楼
    -1.47
     our
    -1.46
     placed
    -1.45
    dė
    -1.43
     indicates
    -1.40
    すな
    -1.39
    POSITIVE LOGITS
    玊
    1.72
    ⍽
    1.71
    According
    1.71
     allerdings
    1.55
    WHY
    1.51
     Meanwhile
    1.48
    综艺
    1.48
    
    1.48
    تیجه
    1.46
    茈
    1.43
    Activations Density 0.073%

    No Known Activations