© 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. 12761
    Prev
    Next
    INDEX
    Explanations

    codes, status, and specific dates

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

    The neuron detects 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
     only
    -1.05
    /'.$
    -1.02
     other
    -1.02
     recomand
    -0.98
     langsung
    -0.97
     turist
    -0.97
     autre
    -0.95
     those
    -0.95
     givet
    -0.92
    それから
    -0.91
    POSITIVE LOGITS
     Straus
    0.94
     σας
    0.92
    riente
    0.92
     sucks
    0.91
    nyataan
    0.91
    差不多
    0.91
     +
    0.89
     З
    0.87
     значит
    0.87
     parere
    0.87
    Activations Density 0.003%

    No Known Activations