© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 20236
    Prev
    Next
    INDEX
    Explanations

    African politics and activists

    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
     glaring
    -1.87
    ํา
    -1.78
    全是
    -1.76
     déclaration
    -1.73
    杈
    -1.71
    有趣的
    -1.70
    是这样的
    -1.70
    ཫ
    -1.69
     einzel
    -1.63
    不做
    -1.62
    POSITIVE LOGITS
    希望
    1.51
    🤙
    1.42
     leng
    1.41
    😓
    1.40
     enn
    1.38
     Nachdem
    1.36
    `/
    1.34
    😇
    1.34
    始
    1.34
    Doge
    1.34
    Activations Density 0.003%

    No Known Activations