© 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. 130516
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly lights up on occurrences of the word “timer” (or close variants) in code or comments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    timer class, interval, event

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    s
    -3.17
    2
    -2.98
    ↵↵
    -2.89
    ↵
    -2.53
    ’
    -2.48
    </sup>
    -2.34
     ซึ่ง
    -2.33
    “
    -2.28
     amd
    -2.28
     et
    -2.22
    POSITIVE LOGITS
    した場合
    2.69
    🍺
    2.59
    🍷
    2.33
    琑
    2.28
    ۸
    2.25
    🌻
    2.23
    🍻
    2.23
     durar
    2.23
    🥂
    2.23
    ストーン
    2.14
    Activations Density 0.002%

    No Known Activations