© 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. 66288
    Prev
    Next
    INDEX
    Explanations

    mechanical components and parts

    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
    tivazione
    -1.30
     cheia
    -1.24
     Teraz
    -1.23
     inclui
    -1.17
    بله
    -1.16
     incluyen
    -1.16
     incluindo
    -1.15
    inverno
    -1.14
    と呼ばれる
    -1.13
     bestemt
    -1.13
    POSITIVE LOGITS
     is
    1.45
    ”？
    1.22
    Etimo
    1.13
    人不
    1.11
     majeure
    1.11
    📡
    1.10
     frivolous
    1.08
     sowohl
    1.06
    CENT
    1.06
     السابق
    1.05
    Activations Density 0.038%

    No Known Activations