© 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. 22-GEMMASCOPE-RES-131K
    7. 71758
    Prev
    Next
    INDEX
    Explanations

    if statements

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

    This neuron detects conditional “if” statements 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_22/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
     vijf
    -1.17
     öner
    -1.12
    underwater
    -1.10
     anunció
    -1.10
    Grazie
    -1.10
     willen
    -1.09
     diverses
    -1.09
     reveló
    -1.05
    worse
    -1.04
    了我
    -1.03
    POSITIVE LOGITS
     there
    1.13
     because
    1.07
     similar
    1.03
     olympique
    1.00
    <>
    0.99
    PARATUS
    0.98
    </b>
    0.98
    १
    0.96
     Typically
    0.96
     simpto
    0.96
    Activations Density 0.002%

    No Known Activations