© 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. 61417
    Prev
    Next
    INDEX
    Explanations

    fund, design, prevent, address, end, maintenance

    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
    当店
    -1.55
    本日の
    -1.54
    今年も
    -1.51
    梦见
    -1.46
    おはよう
    -1.46
    こんばん
    -1.46
    さてさて
    -1.45
    我が家の
    -1.42
    今日の
    -1.38
    tablissements
    -1.38
    POSITIVE LOGITS
     sebagainya
    1.48
     suena
    1.47
     necesito
    1.45
     "
    1.44
    ORATION
    1.34
     récemment
    1.34
     a
    1.32
     anstatt
    1.31
     posiblemente
    1.31
     Wednesday
    1.31
    Activations Density 0.352%

    No Known Activations