© 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. 110890
    Prev
    Next
    INDEX
    Explanations

    data sets and statistics

    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
     There
    -1.97
    7
    -1.94
    6
    -1.48
    i
    -1.47
    5
    -1.40
    if
    -1.38
    y
    -1.38
    4
    -1.38
    e
    -1.38
    There
    -1.38
    POSITIVE LOGITS
    cries
    1.46
    ENEFITS
    1.41
     gänzlich
    1.39
     vrij
    1.38
     pewno
    1.35
    crème
    1.35
     温泉
    1.34
    同士
    1.34
    kimono
    1.33
     crí
    1.30
    Activations Density 0.031%

    No Known Activations