© 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. 66436
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming terms

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

    The neuron fires on numeric tokens and literal numbers (digits and numeric values) in code and text.

    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
     then
    -0.92
     높
    -0.91
    Eerste
    -0.90
     după
    -0.90
    dė
    -0.89
    träd
    -0.86
     prič
    -0.86
     člove
    -0.85
     najbolj
    -0.85
     দেখ
    -0.84
    POSITIVE LOGITS
     may
    1.05
    =''
    1.00
     spans
    0.98
    %;
    0.98
     begun
    0.96
     parts
    0.95
    irmanship
    0.95
     manera
    0.93
     ended
    0.93
     spanning
    0.93
    Activations Density 0.008%

    No Known Activations