© 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. 99730
    Prev
    Next
    INDEX
    Explanations

    moving items and data

    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
     statunit
    -1.52
    牁
    -1.41
     Komis
    -1.37
    🫡
    -1.34
    There
    -1.30
    見
    -1.29
     gik
    -1.29
    ⭐️
    -1.27
    出来ました
    -1.27
    ский
    -1.26
    POSITIVE LOGITS
     Move
    1.83
    move
    1.74
     conquête
    1.56
    moved
    1.54
     Its
    1.51
     Moving
    1.50
     We
    1.48
    籥
    1.48
     และ
    1.46
     législation
    1.45
    Activations Density 0.106%

    No Known Activations