© 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. 34-GEMMASCOPE-RES-131K
    7. 60532
    Prev
    Next
    INDEX
    Explanations

    German and Dutch conjunctions

    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_34/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
    鮠
    -1.98
     parachoque
    -1.95
    bảng
    -1.91
    máy
    -1.88
    Warna
    -1.86
    shrimp
    -1.85
    敺
    -1.81
    bánh
    -1.77
     pérd
    -1.74
    珝
    -1.74
    POSITIVE LOGITS
    l
    2.41
    w
    2.36
    m
    2.33
    h
    2.31
    r
    2.31
    "
    2.30
    c
    2.28
    j
    2.23
    p
    2.23
    a
    2.23
    Activations Density 0.027%

    No Known Activations