© 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. 84097
    Prev
    Next
    INDEX
    Explanations

    code block endings and specific words

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

    The neuron fires on occurrences of “set” (e.g. setter‐method names or standalone set keywords) 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_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
    ḿ
    -1.02
    &=&\
    -0.97
    StandardCharsets
    -0.93
     aranha
    -0.91
    汉
    -0.90
    épendant
    -0.90
    好在
    -0.89
     Até
    -0.89
    ·
    -0.88
    ymm
    -0.88
    POSITIVE LOGITS
     what
    1.04
     transaksi
    1.00
     increases
    0.95
     used
    0.91
     frantically
    0.87
    ↵↵
    0.87
    熾
    0.86
    thető
    0.84
    Фак
    0.84
     has
    0.83
    Activations Density 0.000%

    No Known Activations