© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12581
    Prev
    Next
    INDEX
    Explanations

    already conditions

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

    The neuron activates on numeric literals (numbers) in code.

    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
    λαν
    -0.84
    افظ
    -0.81
     joggers
    -0.80
     Ls
    -0.79
     capitol
    -0.79
     beweisen
    -0.79
     dale
    -0.79
     gärna
    -0.78
     Radioactive
    -0.78
    
    -0.77
    POSITIVE LOGITS
     already
    3.34
    already
    2.61
    Already
    2.59
     уже
    2.53
     Already
    2.50
     bereits
    2.33
    ALREADY
    2.08
     już
    2.05
     ALREADY
    1.98
     вже
    1.98
    Activations Density 0.043%

    No Known Activations