© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130213
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on standalone numeric tokens (integers or decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    list delimiters and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     surpris
    -1.50
     suppos
    -1.48
     estadounid
    -1.48
     prestig
    -1.48
     pittores
    -1.45
    eded
    -1.44
    ebly
    -1.38
     Coloque
    -1.37
     sais
    -1.36
     formid
    -1.36
    POSITIVE LOGITS
     to
    1.89
     not
    1.64
     never
    1.55
     how
    1.54
     getting
    1.49
     gets
    1.42
     use
    1.40
     for
    1.40
     always
    1.38
     its
    1.35
    Activations Density 0.001%

    No Known Activations