© 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. 98551
    Prev
    Next
    INDEX
    Explanations

    conditional statements

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

    This neuron activates on numeric literal tokens (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
    ulary
    -0.93
    ancing
    -0.91
    着的
    -0.90
    matica
    -0.89
    lian
    -0.88
    atory
    -0.86
     rigide
    -0.86
     cei
    -0.85
     emplois
    -0.85
    ometers
    -0.85
    POSITIVE LOGITS
     other
    1.01
     still
    0.96
    Нам
    0.92
     aussieht
    0.92
    에서는
    0.91
     інші
    0.91
    kadang
    0.90
     vertellen
    0.89
     ngược
    0.89
     natomiast
    0.88
    Activations Density 0.005%

    No Known Activations