© 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. 79721
    Prev
    Next
    INDEX
    Explanations

    former state or replacement

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

    This neuron activates on numeric tokens (integers or decimals), i.e. any numbers 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
     Setiap
    -0.92
     Menurut
    -0.91
    癞
    -0.84
     Meskipun
    -0.83
     Bahkan
    -0.83
    Each
    -0.79
    躋
    -0.78
     Закон
    -0.78
    omás
    -0.77
    鮭
    -0.77
    POSITIVE LOGITS
     previous
    1.32
     missing
    1.23
     formerly
    1.16
     former
    1.10
    missing
    1.09
     previously
    1.05
    previous
    1.01
    formerly
    0.97
     substitute
    0.97
     substitutes
    0.94
    Activations Density 0.035%

    No Known Activations