© 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. 34-GEMMASCOPE-RES-131K
    7. 58892
    Prev
    Next
    INDEX
    Explanations

    people smugglers

    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_34/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
    ﺧ
    -1.19
    都要
    -1.17
     sguardo
    -1.15
     może
    -1.14
     child
    -1.13
     player
    -1.13
     owner
    -1.09
     never
    -1.09
     sauté
    -1.08
     anerkannt
    -1.08
    POSITIVE LOGITS
     who
    2.86
     smugglers
    1.52
    cended
    1.39
    Mesmo
    1.39
     الذين
    1.38
    mög
    1.37
    шки
    1.34
     rajut
    1.34
    rechten
    1.34
     sentral
    1.34
    Activations Density 0.052%

    No Known Activations