© 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. 13206
    Prev
    Next
    INDEX
    Explanations

    saving and committing changes

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

    The neuron fires strongly on code‐oriented API calls and keywords having to do with saving or syncing data or object state.

    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
    -0.99
     bestellen
    -0.97
    -0.93
     Seq
    -0.92
     Deleted
    -0.91
     intelligente
    -0.91
     passend
    -0.90
    των
    -0.90
    unica
    -0.90
    chenken
    -0.89
    POSITIVE LOGITS
    保存
    1.06
     save
    1.06
     updates
    1.02
     changes
    1.00
     onSave
    0.98
     saving
    0.93
    更新
    0.93
     without
    0.93
     two
    0.93
     penyimpanan
    0.91
    Activations Density 0.024%

    No Known Activations