© 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. 10-GEMMASCOPE-RES-131K
    7. 87236
    Prev
    Next
    INDEX
    Explanations

    delete operations

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

    The neuron fires on tokens related to deletion operations (e.g. “delete” in function names or SQL DELETE statements).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </strong>
    -1.58
    IN
    -1.48
     interminable
    -1.41
    itized
    -1.41
    s
    -1.39
     bede
    -1.35
     THOSE
    -1.31
    ▫
    -1.31
    ÍTULO
    -1.30
    ativistic
    -1.30
    POSITIVE LOGITS
    ↵
    1.79
     kullanıcı
    1.69
    萏
    1.56
     estadounidenses
    1.45
     escuchadas
    1.44
     Delete
    1.43
     peruano
    1.41
    さんも
    1.41
     يونيو
    1.39
     сказ
    1.38
    Activations Density 0.033%

    No Known Activations