© 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. 33692
    Prev
    Next
    INDEX
    Explanations

    discussion of books and articles

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron selectively fires on longer content words (especially multi‐syllable words), essentially detecting tokens with many characters.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Архивировано
    -1.01
     fortsatt
    -1.00
     uttry
    -0.94
     aastal
    -0.93
    utiny
    -0.91
    кия
    -0.89
     недавно
    -0.89
     packets
    -0.88
     solicitado
    -0.88
    packets
    -0.87
    POSITIVE LOGITS
     chapters
    1.42
     chapter
    1.34
     throughout
    1.25
     Chapters
    1.20
     readers
    1.20
     reader
    1.20
     appendices
    1.16
    Readers
    1.16
    Chapter
    1.15
     discussion
    1.08
    Activations Density 0.048%

    No Known Activations