© 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. 118403
    Prev
    Next
    INDEX
    Explanations

    multi-lingual code and technical terms

    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
    ittoria
    -0.90
    CloseOperation
    -0.87
    isation
    -0.86
    ations
    -0.84
    ation
    -0.82
     Huffman
    -0.82
    enumeration
    -0.81
    arithmetic
    -0.79
    cemia
    -0.79
    nullptr
    -0.78
    POSITIVE LOGITS
     hơn
    1.13
    Abon
    0.98
     more
    0.84
    लिए
    0.80
    Succes
    0.79
    spur
    0.76
     περισσότε
    0.76
    問題は
    0.75
     motto
    0.75
     нее
    0.73
    Activations Density 0.001%

    No Known Activations