© 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. 13553
    Prev
    Next
    INDEX
    Explanations

    company, industry, plant, sales, variables

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

    The neuron fires most strongly on numerical tokens—digits, numbers, and numeric values.

    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
     myself
    -1.09
    dokument
    -1.09
     something
    -1.09
     criaturas
    -1.02
    Dracula
    -1.02
    ̾
    -1.00
    показа
    -0.98
    ūra
    -0.97
     so
    -0.96
    rennt
    -0.96
    POSITIVE LOGITS
    ṇa
    1.34
    ⚋
    1.32
    ⚌
    1.29
    ifferentiated
    1.28
    ty
    1.23
    het
    1.17
     costs
    1.15
    chet
    1.11
     production
    1.11
     product
    1.11
    Activations Density 0.012%

    No Known Activations