© 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. 111061
    Prev
    Next
    INDEX
    Explanations

    buying and selling

    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
     Senin
    -0.93
     Inches
    -0.86
     Infrastruktur
    -0.85
    Republic
    -0.83
     negatif
    -0.82
    绢
    -0.82
     sibuk
    -0.82
    เนื้อ
    -0.82
    ÉE
    -0.81
    forcement
    -0.81
    POSITIVE LOGITS
     our
    1.13
     we
    1.13
     purchase
    1.06
     buying
    0.94
     podríamos
    0.92
     decimos
    0.87
     tendremos
    0.87
     We
    0.87
     creemos
    0.85
     wszystkie
    0.83
    Activations Density 0.006%

    No Known Activations