© 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. 38596
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

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

    This neuron detects numeric tokens (individual 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_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
    RETRY
    -0.78
     BaseActivity
    -0.75
    essai
    -0.75
    Cooldown
    -0.72
    Glej
    -0.71
    écriture
    -0.70
     Theod
    -0.70
     susi
    -0.69
    מלי
    -0.69
     agre
    -0.68
    POSITIVE LOGITS
     ۱۰
    1.06
    ۱۰
    0.90
     ten
    0.85
     tenth
    0.80
    第十
    0.79
    十
    0.74
     Loyalty
    0.72
    сихо
    0.71
    withOpacity
    0.69
    eleven
    0.68
    Activations Density 0.063%

    No Known Activations