© 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. 105924
    Prev
    Next
    INDEX
    Explanations

    .md files

    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
     già
    -1.51
    by
    -1.50
    観て
    -1.49
    つた
    -1.44
    we
    -1.42
     beschleun
    -1.42
    圌
    -1.40
    嵓
    -1.39
     getNome
    -1.39
     Their
    -1.36
    POSITIVE LOGITS
    自行车
    1.71
     lyd
    1.45
     œufs
    1.40
    strijd
    1.40
    стью
    1.40
     cómoda
    1.38
    늪
    1.35
     exclusivamente
    1.34
    别人的
    1.34
    驀
    1.33
    Activations Density 0.050%

    No Known Activations