© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 742
    Prev
    Next
    INDEX
    Explanations

    SQL table updates and declarations

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

    The neuron fires on uppercase SQL/DDL code tokens (like CREATE, TABLE, VARCHAR, NOT NULL, and numeric literals) indicating snippets of SQL schema or code definitions.

    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
    AddWithValue
    -0.82
    вів
    -0.77
    нибудь
    -0.75
    Thong
    -0.75
    bangun
    -0.74
     Malone
    -0.74
    likleri
    -0.73
    tanleria
    -0.73
    expectedResult
    -0.70
     zákaz
    -0.70
    POSITIVE LOGITS
     oracle
    1.05
    oracle
    0.91
     Oracle
    0.82
    Oracle
    0.79
     oracles
    0.78
    koa
    0.76
     Marjorie
    0.75
    SCN
    0.75
     terminator
    0.74
    を変
    0.73
    Activations Density 0.049%

    No Known Activations