© 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. 68180
    Prev
    Next
    INDEX
    Explanations

    for loop

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

    The neuron activates on occurrences of the keyword “for,” especially when used to introduce a for-loop.

    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
     the
    -3.13
    えっ
    -2.73
    うわ
    -2.53
    あぁ
    -2.52
     our
    -2.47
    ＊＊＊＊
    -2.41
    すみません
    -2.38
    からお
    -2.38
    おわりに
    -2.38
    ＊＊＊
    -2.33
    POSITIVE LOGITS
    u
    2.36
    s
    2.13
    <bos>
    1.95
    そのため
    1.94
     They
    1.90
    ,
    1.88
    r
    1.87
    遑
    1.80
    斡
    1.77
    ༘
    1.75
    Activations Density 0.071%

    No Known Activations