© 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. 9558
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

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

    The neuron fires 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_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
    âts
    -0.98
     how
    -0.97
     馆
    -0.88
    StringUtils
    -0.83
     тех
    -0.83
    八年
    -0.83
     fuß
    -0.82
     сред
    -0.82
     You
    -0.81
     наиболее
    -0.80
    POSITIVE LOGITS
     TOWER
    0.98
    росла
    0.84
    ぴ
    0.83
    Istituto
    0.83
     geheim
    0.82
    ísima
    0.82
    애
    0.82
    tijden
    0.81
    kunft
    0.80
    stunden
    0.80
    Activations Density 0.102%

    No Known Activations