© 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. 22-GEMMASCOPE-RES-131K
    7. 67313
    Prev
    Next
    INDEX
    Explanations

    variables, indices, and equations

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

    This neuron responds to numeric tokens (i.e. any token containing digits).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     السياس
    -1.00
    ování
    -0.99
     servicios
    -0.98
     recomand
    -0.97
     только
    -0.94
    maries
    -0.94
    <bos>
    -0.94
     stronę
    -0.93
    đồng
    -0.93
    ajinan
    -0.93
    POSITIVE LOGITS
    為に
    1.02
    の作成
    0.99
     verschieden
    0.96
    際は
    0.94
    ためには
    0.93
    際の
    0.92
    擱
    0.91
    する方法
    0.90
     Многие
    0.89
     Каждый
    0.88
    Activations Density 0.012%

    No Known Activations