© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3564
    Prev
    Next
    INDEX
    Explanations

    Ukraine and Zelensky

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

    The neuron is specifically detecting the digit “0” in the text.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     which
    -1.55
     not
    -1.48
     how
    -1.35
     both
    -1.34
     there
    -1.34
     found
    -1.30
     never
    -1.27
     although
    -1.26
     especially
    -1.25
     other
    -1.22
    POSITIVE LOGITS
     ۲
    1.77
    Ukraine
    1.57
     Ukraine
    1.55
     Ukrainians
    1.54
     Zelensky
    1.38
     Ukrainian
    1.37
     Omicron
    1.30
     metaverse
    1.30
     Inflation
    1.28
    Ukrainian
    1.27
    Activations Density 0.063%

    No Known Activations