© 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. 33232
    Prev
    Next
    INDEX
    Explanations

    numeric prefixes and identifiers

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

    This neuron detects programming code snippets, especially function‐call patterns and snake_case identifiers with punctuation typical of source 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_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
     yakin
    -0.92
     mev
    -0.91
     yyq
    -0.89
     照片
    -0.82
     hvid
    -0.82
     quince
    -0.81
    стема
    -0.80
    犠
    -0.80
     pronunci
    -0.79
    unun
    -0.79
    POSITIVE LOGITS
    ビーチ
    0.84
     maybe
    0.83
    khi
    0.79
    lton
    0.79
     something
    0.78
     erweit
    0.78
     beach
    0.77
    ਊ
    0.75
     late
    0.75
     đối
    0.71
    Activations Density 0.012%

    No Known Activations