© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27568
    Prev
    Next
    INDEX
    Explanations

    Programming and technical questions

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

    The neuron fires on numeric literal tokens (i.e. numbers) 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_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
     dispositivo
    -1.09
    startswith
    -0.94
    önt
    -0.84
     табле
    -0.84
     if
    -0.84
     शुरु
    -0.84
     ennemi
    -0.84
     եր
    -0.84
     for
    -0.83
     first
    -0.83
    POSITIVE LOGITS
     Бе
    1.04
    érica
    0.91
    stwa
    0.88
     rurale
    0.87
     левый
    0.87
     فور
    0.87
     великолеп
    0.87
    噻
    0.85
     reaccion
    0.85
     habia
    0.85
    Activations Density 0.002%

    No Known Activations