© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57360
    Prev
    Next
    INDEX
    Explanations

    conditional code structures

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

    The neuron is strongly triggered by numeric literals (numbers) 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
     otherwise
    -3.05
    Otherwise
    -2.72
     Otherwise
    -2.64
    otherwise
    -2.45
     else
    -2.38
     OTHERWISE
    -2.09
     иначе
    -2.06
    否则
    -2.03
     sonst
    -1.91
     jinak
    -1.88
    POSITIVE LOGITS
     Either
    1.35
    either
    1.20
    Either
    1.13
     Regardless
    1.13
     either
    1.11
    いずれ
    1.01
     любом
    0.98
     regardless
    0.95
     both
    0.94
    Regardless
    0.90
    Activations Density 0.005%

    No Known Activations