© 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. 34-GEMMASCOPE-RES-131K
    7. 91646
    Prev
    Next
    INDEX
    Explanations

    conditional statements or blocks

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

    This neuron detects conditional statements, in particular the keyword “if” (i.e. code branches).

    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
    шње
    -1.08
    🐆
    -1.02
     matériaux
    -0.96
     män
    -0.96
     ALREADY
    -0.95
    whose
    -0.93
     putea
    -0.93
     église
    -0.92
    愀
    -0.92
    klara
    -0.91
    POSITIVE LOGITS
     need
    1.32
     should
    1.05
     needs
    1.02
    需要
    0.98
     using
    0.95
     use
    0.91
     Always
    0.90
     show
    0.89
     include
    0.88
    ),
    0.87
    Activations Density 0.007%

    No Known Activations