© 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. 92974
    Prev
    Next
    INDEX
    Explanations

    exceptions and contrasts

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

    The neuron activates on numeric tokens (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_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
    じゃなくて
    -0.87
    でもいい
    -0.85
     both
    -0.83
    足り
    -0.80
     loại
    -0.79
     testé
    -0.76
    rücke
    -0.75
    って何
    -0.75
    𝑌
    -0.75
     oeufs
    -0.74
    POSITIVE LOGITS
     which
    2.45
     where
    1.84
    which
    1.34
    ซึ่ง
    1.34
     ambayo
    1.30
     حيث
    1.27
     whereupon
    1.24
     которые
    1.24
     wherein
    1.23
     jossa
    1.20
    Activations Density 0.088%

    No Known Activations