© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107949
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and structures

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

    The main thing this neuron does is detect numeric literal tokens (integer constants) 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
     advisers
    -0.93
     advisors
    -0.91
     advisor
    -0.79
    峒
    -0.79
    $$
    -0.77
    顧問
    -0.77
     mentors
    -0.77
     ?</
    -0.76
    ıştı
    -0.73
     advisory
    -0.72
    POSITIVE LOGITS
     éstos
    0.75
     Persson
    0.75
    ainted
    0.75
    LOCK
    0.74
     iedereen
    0.74
     говорится
    0.73
     geprüft
    0.72
     EL
    0.72
    是我们
    0.72
     広
    0.71
    Activations Density 0.003%

    No Known Activations