© 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. 28592
    Prev
    Next
    INDEX
    Explanations

    code definitions and questions

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

    The neuron fires on code tokens that mark function or method declarations and their return types in programming 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
    تس
    -1.09
    ༴
    -1.07
     baratas
    -1.07
    ༼
    -1.06
    鸲
    -1.05
     there
    -1.05
     itens
    -1.02
     plát
    -0.98
    their
    -0.98
     roja
    -0.98
    POSITIVE LOGITS
    起来的
    1.27
    Bjs
    0.96
    员
    0.93
    ErrorException
    0.91
    时的
    0.90
    isiä
    0.90
     tele
    0.90
     dadurch
    0.89
    چھ
    0.89
    M
    0.87
    Activations Density 0.000%

    No Known Activations