© 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. 211
    Prev
    Next
    INDEX
    Explanations

    mathematical definitions and definitions

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

    This neuron activates on numeric tokens (digits or numerical expressions) 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_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
     different
    -1.01
     фаса
    -0.88
     from
    -0.86
    Phas
    -0.85
    !=
    -0.85
     variasi
    -0.85
    sä
    -0.85
    isław
    -0.84
     beban
    -0.84
     می‌گو
    -0.83
    POSITIVE LOGITS
    ञ
    0.92
    Վ
    0.91
     пользователем
    0.90
    BOURNE
    0.90
     требу
    0.90
    вказ
    0.89
    ம
    0.88
     want
    0.86
     francisco
    0.86
    神宮
    0.86
    Activations Density 0.018%

    No Known Activations