© 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. 67343
    Prev
    Next
    INDEX
    Explanations

    code or section headings

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

    This neuron fires on code‐specific punctuation and delimiters (e.g. commas, parentheses) in programming snippets.

    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
     inmun
    -0.96
    ="")
    -0.94
     sewa
    -0.93
     destinée
    -0.93
    艫
    -0.92
    咂
    -0.92
     खुद
    -0.91
    )==
    -0.91
     exemplos
    -0.91
     puerto
    -0.90
    POSITIVE LOGITS
    ՛
    0.90
    inian
    0.86
    
    0.84
     güne
    0.82
    ֲ
    0.82
     после
    0.81
    liminaries
    0.81
     leur
    0.80
     nadzie
    0.80
     یکی
    0.79
    Activations Density 0.001%

    No Known Activations