© 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. 10-GEMMASCOPE-RES-131K
    7. 42767
    Prev
    Next
    INDEX
    Explanations

    variable i in loops

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

    The neuron fires on occurrences of the loop‐counter variable “i” (especially in for-loop headers and array indexing).

    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
    ,”
    -2.53
    …”
    -2.22
    —“
    -2.19
     exquisitely
    -2.05
    and
    -2.05
     not
    -2.03
    —”
    -2.03
    此时
    -2.02
    鸯
    -1.98
    to
    -1.97
    POSITIVE LOGITS
    缡
    2.61
     was
    2.53
     だけ
    2.48
     เมื่อ
    2.34
     estava
    2.28
    艄
    2.20
     are
    2.16
    歘
    2.14
    
    2.14
     ใน
    2.13
    Activations Density 0.021%

    No Known Activations