© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104613
    Prev
    Next
    INDEX
    Explanations

    year ranges ending in present

    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
     for
    -1.78
     if
    -1.55
     by
    -1.48
     in
    -1.44
     with
    -1.30
     aport
    -1.27
     derives
    -1.23
     within
    -1.22
    .''
    -1.20
     precedes
    -1.20
    POSITIVE LOGITS
    訁
    1.61
    Since
    1.58
    about
    1.49
    inière
    1.49
    since
    1.48
    孩子的
    1.36
    mism
    1.34
    本当に
    1.33
    maries
    1.33
    استفاده
    1.32
    Activations Density 0.014%

    No Known Activations