© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30058
    Prev
    Next
    INDEX
    Explanations

    if err != nil

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

    The neuron fires on occurrences of the “if” keyword (i.e. conditional statements) in Go code.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ：【
    -1.05
     WHILE
    -1.05
     plát
    -1.03
    whereas
    -1.02
     گفتم
    -1.00
    mucho
    -0.95
    Евгений
    -0.94
     luxus
    -0.94
    certainly
    -0.93
     dispara
    -0.90
    POSITIVE LOGITS
     !
    1.88
    !
    1.55
     _,
    1.50
     len
    1.35
     !(
    1.34
     ;
    1.21
     err
    1.16
     strings
    1.13
    len
    1.08
    _,
    1.06
    Activations Density 0.002%

    No Known Activations