© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67090
    Prev
    Next
    INDEX
    Explanations

    programming for loops

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

    The neuron is specialized to pick out the increment clause (e.g. the “i++” or “++i”) in a for-loop header.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     "
    -2.22
    >
    -1.81
    就开始
    -1.73
     deux
    -1.63
     большую
    -1.62
    只是一
    -1.59
    要做
    -1.59
     ручной
    -1.57
    ついで
    -1.56
    ↵
    -1.55
    POSITIVE LOGITS
    días
    1.55
    比如
    1.48
    Dzięki
    1.44
    Bardzo
    1.43
    因为
    1.42
     先生
    1.41
     individuelles
    1.41
    ziem
    1.41
    Polecam
    1.41
     разом
    1.41
    Activations Density 0.002%

    No Known Activations