© 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. 34-GEMMASCOPE-RES-131K
    7. 11875
    Prev
    Next
    INDEX
    Explanations

    nested loops with i and j

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

    The neuron fires on occurrences of “for” loop headers 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_34/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
    Suivez
    -0.90
    eighth
    -0.90
     primeiro
    -0.88
    以外の
    -0.87
     couverte
    -0.86
    ᄋ
    -0.85
    offrir
    -0.84
    zard
    -0.84
     randint
    -0.82
    ₁,
    -0.81
    POSITIVE LOGITS
     j
    1.55
    j
    1.13
     J
    1.06
     second
    0.81
    J
    0.73
     paulista
    0.70
    arty
    0.69
     agradable
    0.69
     gunung
    0.68
    jButton
    0.66
    Activations Density 0.012%

    No Known Activations