© 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. 36019
    Prev
    Next
    INDEX
    Explanations

    quantities or numbers

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

    This neuron activates on numeric tokens (numbers and decimal 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
     four
    -1.63
     five
    -1.51
     three
    -1.44
     six
    -1.13
     चार
    -1.10
     seven
    -0.99
     Four
    -0.98
     eight
    -0.98
     Five
    -0.94
     two
    -0.93
    POSITIVE LOGITS
    thousands
    1.49
     thousands
    1.48
    Thousands
    1.37
     milliers
    1.28
    hundreds
    1.25
     milhares
    1.20
     ogrom
    1.15
     millions
    1.12
     centaines
    1.07
     hundreds
    1.04
    Activations Density 0.107%

    No Known Activations