© 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. 38384
    Prev
    Next
    INDEX
    Explanations

    syntax delimiters

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

    The neuron fires on numeric literals (digits) 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
    quese
    -0.93
     Tecnologia
    -0.88
     ônibus
    -0.87
    涪
    -0.81
    rió
    -0.80
    hapsody
    -0.79
    
    -0.77
    chádz
    -0.76
    REASONS
    -0.75
    kologie
    -0.75
    POSITIVE LOGITS
     same
    1.13
    same
    0.94
     твой
    0.92
    同上
    0.92
    樣的
    0.92
     pareil
    0.91
     elektrische
    0.89
    給你
    0.89
    Same
    0.88
     Same
    0.88
    Activations Density 0.021%

    No Known Activations