© 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. 115684
    Prev
    Next
    INDEX
    Explanations

    reuse, recycled, reusable

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

    The neuron activates on numeric tokens—i.e. it detects numbers (quantities, percentages, reference numerals) 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
    řejmě
    -0.86
    prayer
    -0.82
    瘪
    -0.81
    смотрим
    -0.77
     Relevance
    -0.75
     Fraser
    -0.73
    tigas
    -0.73
     sõ
    -0.71
    zle
    -0.70
    olving
    -0.69
    POSITIVE LOGITS
     reuse
    6.41
     reused
    5.56
     Reuse
    5.00
    reuse
    4.88
    Reuse
    4.88
     reusable
    4.31
     reutiliz
    3.97
     Reusable
    3.36
     recycling
    3.23
     recycled
    3.09
    Activations Density 0.143%

    No Known Activations