© 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. 86243
    Prev
    Next
    INDEX
    Explanations

    maintain

    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
     Kedua
    -1.59
    뿍
    -1.53
    并未
    -1.50
     Fakta
    -1.50
     Bukan
    -1.48
     Soal
    -1.45
    صالات
    -1.44
    𓋼
    -1.43
     geho
    -1.41
    ”
    -1.41
    POSITIVE LOGITS
     mengirimkan
    1.55
     a
    1.55
    It
    1.52
     över
    1.43
    m
    1.42
     mendorong
    1.38
     fourni
    1.38
    this
    1.36
    n
    1.35
     comercio
    1.31
    Activations Density 0.023%

    No Known Activations