© 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. 83609
    Prev
    Next
    INDEX
    Explanations

    code and legal phrases

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

    This neuron activates on numeric tokens (digit sequences) in the text.

    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
     both
    -0.82
     severally
    -0.81
    issimo
    -0.78
     yalnız
    -0.77
    真相
    -0.76
    gı
    -0.75
    شنگ
    -0.75
     rigue
    -0.74
     adoptar
    -0.74
     compartió
    -0.74
    POSITIVE LOGITS
    urbs
    0.84
     ذات
    0.83
     Iv
    0.79
    dAtA
    0.78
     يش
    0.78
    为什么会
    0.77
     বি
    0.77
     DVDs
    0.75
    szön
    0.75
     SAME
    0.74
    Activations Density 0.001%

    No Known Activations