© 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. 87129
    Prev
    Next
    INDEX
    Explanations

    incrementing or summing variables

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

    The neuron is detecting numeric literals (digit sequences) in 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
    }),
    -1.09
     which
    -1.05
    )]{
    -1.02
     it
    -0.94
    をご覧ください
    -0.93
    eddable
    -0.92
     aulas
    -0.90
    uanto
    -0.89
     clientes
    -0.86
    ╝
    -0.85
    POSITIVE LOGITS
     semacam
    0.87
     Rine
    0.84
     Soprano
    0.84
    uran
    0.83
    ticello
    0.83
     +
    0.82
    flor
    0.82
    덥
    0.81
    🗸
    0.81
     zowel
    0.81
    Activations Density 0.014%

    No Known Activations