© 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. 49902
    Prev
    Next
    INDEX
    Explanations

    words in code

    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
     Notation
    -0.94
     betek
    -0.93
    notation
    -0.92
    ？（
    -0.87
     notation
    -0.85
    marginBottom
    -0.83
    ceiro
    -0.83
     дета
    -0.83
     notations
    -0.82
     shorthand
    -0.82
    POSITIVE LOGITS
     word
    2.33
     words
    2.30
    Word
    1.83
     Word
    1.82
     Words
    1.63
    Words
    1.55
    word
    1.48
     palabras
    1.40
    单词
    1.39
     vocabulary
    1.38
    Activations Density 0.153%

    No Known Activations