© 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. 53817
    Prev
    Next
    INDEX
    Explanations

    match patterns and code constructs

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

    The neuron strongly activates on tokens that are numeric literals (multi‐digit numbers) within code snippets.

    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
     this
    -0.85
    composed
    -0.80
    immunity
    -0.78
     Тя
    -0.77
    PLICATIONS
    -0.76
    endgroup
    -0.74
    nothing
    -0.73
     Стар
    -0.73
    []
    -0.73
     Straßen
    -0.72
    POSITIVE LOGITS
     if
    1.26
    match
    1.06
    Self
    1.05
     match
    0.98
    format
    0.98
     Some
    0.94
    Some
    0.91
     format
    0.90
     some
    0.90
     Self
    0.90
    Activations Density 0.005%

    No Known Activations