© 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. 58934
    Prev
    Next
    INDEX
    Explanations

    coordinates and commas

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

    The neuron fires on numeric literals (number tokens) 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_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
     Lazio
    -0.88
     Antiqu
    -0.87
     PREG
    -0.82
     PRINCE
    -0.81
     Pistons
    -0.80
     pensioners
    -0.78
    vanju
    -0.77
     précisément
    -0.77
     Realtors
    -0.76
     anisotropy
    -0.76
    POSITIVE LOGITS
    Directory
    0.85
    Sixty
    0.85
    yid
    0.85
     random
    0.84
     ground
    0.80
     disfru
    0.80
     date
    0.79
    agory
    0.79
    random
    0.77
    нять
    0.76
    Activations Density 0.006%

    No Known Activations