© 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. 10-GEMMASCOPE-RES-131K
    7. 90827
    Prev
    Next
    INDEX
    Explanations

    markup or code formatting

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

    The neuron strongly activates on numeric tokens (digits or 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_10/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
     When
    -2.88
    when
    -2.34
     one
    -2.33
     soothing
    -2.20
     cheerful
    -2.19
     it
    -2.14
     seven
    -2.14
     two
    -2.11
     lavish
    -2.08
     Before
    -2.00
    POSITIVE LOGITS
    '
    2.83
    ’
    2.50
     置物
    2.30
    ",
    2.25
    尤其
    2.19
     culmin
    2.19
    羮
    2.03
     focuses
    2.02
    ."
    2.00
     使っ
    1.98
    Activations Density 0.008%

    No Known Activations