© 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. 60278
    Prev
    Next
    INDEX
    Explanations

    Huffman coding and compression

    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
     missing
    -1.70
    missing
    -1.49
     Missing
    -1.40
    Missing
    -1.37
     MISSING
    -1.11
    MISSING
    -0.83
     пропа
    -0.81
    olyb
    -0.77
    AddArg
    -0.75
    coccal
    -0.73
    POSITIVE LOGITS
     Huffman
    1.39
     frequency
    1.17
     frequencies
    1.09
    Huff
    1.07
     hu
    1.07
     Huf
    1.04
    Frequency
    1.04
     Frequency
    1.03
     Huff
    1.02
    frequency
    0.98
    Activations Density 0.011%

    No Known Activations