© 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. 22-GEMMASCOPE-RES-131K
    7. 64444
    Prev
    Next
    INDEX
    Explanations

    number of entities

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

    The neuron is keyed to spotting standalone numeric tokens (i.e. numbers) 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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    蛧
    -1.77
    henswürdigkeiten
    -1.54
    
    -1.50
     fará
    -1.44
    ↵
    -1.43
    があった
    -1.43
    了许多
    -1.38
    着自己的
    -1.38
     martens
    -1.33
     zrobić
    -1.32
    POSITIVE LOGITS
     of
    2.14
     different
    1.64
     antiguas
    1.54
     españoles
    1.51
     &
    1.49
    D
    1.37
    にします
    1.34
     cercanos
    1.34
     ofthe
    1.34
     únicas
    1.33
    Activations Density 0.097%

    No Known Activations