© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103708
    Prev
    Next
    INDEX
    Explanations

    truss bridge, Tyson Foods, USS ship

    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
     ‎
    -2.69
    actéristi
    -2.55
    ↵
    -2.53
     dergleichen
    -2.52
     contrasting
    -2.44
     einfacher
    -2.44
     kleines
    -2.42
    欵
    -2.42
    刪除
    -2.42
     Considered
    -2.41
    POSITIVE LOGITS
    埽
    3.44
    🍻
    3.03
    k
    2.70
    😈
    2.69
    💃
    2.63
     walang
    2.63
    😝
    2.63
     BRARY
    2.53
    🧍
    2.52
     車場
    2.44
    Activations Density 0.004%

    No Known Activations