© 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. 59042
    Prev
    Next
    INDEX
    Explanations

    business and financial reports

    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
     罗
    -0.82
    طيع
    -0.80
     efficiently
    -0.75
     shouldn
    -0.74
    第二个
    -0.74
     cà
    -0.69
     Кроме
    -0.68
    のですが
    -0.67
    蒐
    -0.67
     unbekannt
    -0.66
    POSITIVE LOGITS
    
    0.96
    cientes
    0.91
    rounding
    0.91
    warn
    0.88
     proprietor
    0.87
    गे
    0.86
     Warn
    0.86
    icans
    0.86
     totals
    0.85
    öhnen
    0.85
    Activations Density 0.022%

    No Known Activations