© 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. 45599
    Prev
    Next
    INDEX
    Explanations

    word origins and meanings

    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
     alcune
    -1.00
     erfü
    -0.97
     alcuni
    -0.96
     singola
    -0.96
     ausreich
    -0.96
     inglés
    -0.91
     trataba
    -0.91
     volontà
    -0.91
     giusta
    -0.90
    Симпто
    -0.89
    POSITIVE LOGITS
     word
    1.37
     term
    1.25
     meaning
    1.23
    language
    1.19
     for
    1.18
     language
    1.17
     equivalent
    1.16
     words
    1.12
     equivalents
    1.11
    word
    1.03
    Activations Density 0.049%

    No Known Activations