© 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. 41
    Prev
    Next
    INDEX
    Explanations

    sheet or layer structures

    np_acts-logits-general · gemini-2.5-flash-lite

    words related to layered materials or structures, particularly terms like "layer," "sheet," "slab," and similar physical arrangements.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ディション
    -1.52
    ذت
    -1.38
    他的
    -1.38
     装修
    -1.35
    matitis
    -1.34
    ウンド
    -1.34
     hır
    -1.32
    orail
    -1.31
    резать
    -1.30
     rocha
    -1.30
    POSITIVE LOGITS
    '
    1.94
    酒吧
    1.55
     acoged
    1.51
     your
    1.46
     that
    1.42
     nødvendig
    1.41
     desvan
    1.41
     notably
    1.40
     Preise
    1.39
     utilizan
    1.38
    Activations Density 0.122%

    No Known Activations