© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34653
    Prev
    Next
    INDEX
    Explanations

    multilingual abbreviations and acronyms

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

    The neuron fires on standalone uppercase alphanumeric tokens (abbreviations or codes) such as currency/signal/register identifiers.

    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
     in
    -2.08
    を
    -1.91
    を含む
    -1.41
    が
    -1.38
    景色
    -1.32
    への
    -1.28
     globos
    -1.28
    捗
    -1.27
    を持つ
    -1.24
     estrena
    -1.20
    POSITIVE LOGITS
     مختلف
    1.29
    メルカリ
    1.28
     verschill
    1.23
    lawayo
    1.21
    食べたい
    1.21
    お世話
    1.20
     россии
    1.20
     różnych
    1.20
    aritions
    1.20
     olika
    1.19
    Activations Density 0.056%

    No Known Activations