© 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. 69997
    Prev
    Next
    INDEX
    Explanations

    two, three, 2, 3

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

    The main thing this neuron does is detect numeric tokens (e.g. numbers, digits, or numeric constants) 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
     fifty
    -1.47
     seventy
    -1.38
     sixty
    -1.38
     eighty
    -1.30
     forty
    -1.27
     hundreds
    -1.24
    Hundreds
    -1.21
    twenty
    -1.20
    Twenty
    -1.19
     thousands
    -1.17
    POSITIVE LOGITS
     two
    4.22
     två
    3.13
    two
    3.09
     three
    3.09
    TWO
    2.84
     zwei
    2.81
    Two
    2.78
     TWO
    2.75
     deux
    2.69
     δύο
    2.69
    Activations Density 0.108%

    No Known Activations