© 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. 22-GEMMASCOPE-RES-131K
    7. 98504
    Prev
    Next
    INDEX
    Explanations

    depends on

    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_22/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
     cette
    -1.59
    titure
    -1.54
    this
    -1.52
    inctions
    -1.48
    ляции
    -1.46
     dieser
    -1.38
     semua
    -1.37
    焄
    -1.36
    薅
    -1.36
     này
    -1.36
    POSITIVE LOGITS
    .
    1.70
    ت
    1.53
     Traducción
    1.47
    \
    1.44
    𝐃
    1.39
    (
    1.34
    you
    1.27
    “
    1.24
    {
    1.23
    You
    1.23
    Activations Density 0.011%

    No Known Activations