© 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. 22-GEMMASCOPE-RES-131K
    7. 54230
    Prev
    Next
    INDEX
    Explanations

    if else statements

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

    The neuron is detecting long runs of leading whitespace (indentation) 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
     from
    -1.55
     menyen
    -1.12
    申し上げます
    -1.12
     to
    -1.09
    Վ
    -1.07
    逛
    -1.06
    ബ
    -1.00
     via
    -1.00
     ocurrió
    -0.99
    المل
    -0.98
    POSITIVE LOGITS
     else
    1.19
    ほんとに
    1.16
    already
    1.15
    こっち
    1.13
     hjel
    1.12
     heuti
    1.10
     situatie
    1.09
    に追加
    1.06
    の準備
    1.05
     corazones
    1.05
    Activations Density 0.005%

    No Known Activations