© 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. 102378
    Prev
    Next
    INDEX
    Explanations

    free, delete, plugged

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

    This neuron detects memory‐deallocation operations (calls to delete or free).

    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
    copy
    -0.86
    cleanup
    -0.85
     Disposal
    -0.84
     deleting
    -0.83
    回收
    -0.81
    Cleanup
    -0.80
     cleanup
    -0.79
    delete
    -0.77
     delete
    -0.77
     deletes
    -0.76
    POSITIVE LOGITS
     free
    1.95
    free
    1.68
    FREE
    1.30
     FREE
    1.25
    免费
    1.06
     Free
    1.06
    Free
    1.06
    免費
    1.05
    無料で
    0.98
     беспла
    0.92
    Activations Density 0.006%

    No Known Activations