© 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. 34-GEMMASCOPE-RES-131K
    7. 76090
    Prev
    Next
    INDEX
    Explanations

    code comments and code structures

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

    The neuron is a “code‐detector” – it fires on tokens that look like programming identifiers, file or module names, license keywords, etc., rather than ordinary prose words.

    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
    Cai
    -0.70
     corrosive
    -0.65
     Océ
    -0.64
     Bono
    -0.63
    Zag
    -0.61
    (){}
    -0.61
    通行
    -0.60
    Calli
    -0.60
    вест
    -0.60
     gạo
    -0.60
    POSITIVE LOGITS
    धि
    0.74
    фа
    0.69
    amsa
    0.67
    Hamilton
    0.67
     Medford
    0.66
    Ӯ
    0.65
     Cyclops
    0.65
     abrazo
    0.65
     område
    0.64
     قوان
    0.64
    Activations Density 0.071%

    No Known Activations