© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8898
    Prev
    Next
    INDEX
    Explanations

    sql select from clause

    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
    ↵↵
    -1.75
    ichtete
    -1.62
    1
    -1.59
     
    -1.45
     last
    -1.41
    最
    -1.36
     dernières
    -1.35
     was
    -1.35
     doesn
    -1.34
    Doesn
    -1.33
    POSITIVE LOGITS
     mereka
    1.82
     them
    1.73
    韡
    1.58
     setiap
    1.54
     moviliz
    1.52
     nineteen
    1.48
     Popis
    1.46
     肖像
    1.45
     összefoglaló
    1.45
     reconoc
    1.45
    Activations Density 0.013%

    No Known Activations