© 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. 10932
    Prev
    Next
    INDEX
    Explanations

    SQL, programming statements, or questions

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

    This neuron responds to programming-style identifiers and keywords (e.g. SQL keywords like DROP, TABLE, IF; class/variable names like Smart, Proxy, View; and other code tokens).

    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
     camisas
    -1.13
     écoute
    -0.94
     mochilas
    -0.93
     máscaras
    -0.91
    صیلات
    -0.91
     celebridades
    -0.91
     accion
    -0.91
     muze
    -0.91
    taille
    -0.91
     dinoss
    -0.90
    POSITIVE LOGITS
    cancel
    1.00
    pes
    0.93
    Z
    0.92
     verwendeten
    0.91
    剧照
    0.91
    che
    0.90
     erwähnten
    0.89
    britanni
    0.89
    jak
    0.88
     PKK
    0.88
    Activations Density 0.001%

    No Known Activations