© 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. 66163
    Prev
    Next
    INDEX
    Explanations

    POS, cash, and registers

    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
     چیه
    -0.72
    élaboration
    -0.69
    لينا
    -0.69
    devším
    -0.68
    ƺ
    -0.67
    şik
    -0.66
    لاء
    -0.66
     коллек
    -0.65
    Alguns
    -0.65
     Produktion
    -0.64
    POSITIVE LOGITS
     POS
    1.29
    POS
    1.09
     tills
    1.03
     Epson
    1.00
     pos
    0.98
     hospitality
    0.96
     Pos
    0.94
     till
    0.91
     Aberdeen
    0.91
     NCR
    0.91
    Activations Density 0.021%

    No Known Activations