© 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. 117991
    Prev
    Next
    INDEX
    Explanations

    code comments and structure

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

    The neuron strongly activates on numeric tokens (i.e. any standalone digits or digit sequences) in code or comments.

    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
    MyApp
    -0.88
     istore
    -0.83
    produzione
    -0.79
    しやすい
    -0.79
    していました
    -0.79
    خخ
    -0.78
    mẫu
    -0.76
    してた
    -0.76
    Mereka
    -0.75
    כד
    -0.75
    POSITIVE LOGITS
    Breakpoint
    0.86
     aload
    0.86
     キャ
    0.84
    货
    0.84
                        
    0.83
    ⅱ
    0.82
     ゲ
    0.81
    先
    0.81
    สำ
    0.81
     kilomètres
    0.81
    Activations Density 0.004%

    No Known Activations