© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 58811
    Prev
    Next
    INDEX
    Explanations

    citations and references

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

    The neuron responds to numeric tokens and hyphens, i.e. the digit sequences (years, page numbers, ranges) and their separators common in citations.

    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
     now
    -1.27
     after
    -1.01
     día
    -0.95
     seemingly
    -0.94
     before
    -0.92
     as
    -0.92
     compelling
    -0.91
     sophisticated
    -0.91
     specific
    -0.90
     valuable
    -0.90
    POSITIVE LOGITS
     gebaut
    0.99
     régal
    0.93
     Fourteen
    0.90
     worin
    0.90
     vieler
    0.88
    isons
    0.88
     ongel
    0.88
    matite
    0.88
     Eighteen
    0.85
     getestet
    0.85
    Activations Density 0.005%

    No Known Activations