© 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. 10-GEMMASCOPE-RES-131K
    4. 105406
    Prev
    Next
    INDEX
    Explanations

    sqlite3

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

    references to SQLite3 in code and technical documentation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on occurrences of “sqlite” (often paired with “3” or version‐related flags), i.e. it detects references to the SQLite 3 database system.

    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
    </b>
    -3.03
     This
    -2.55
     That
    -2.19
    </td>
    -2.17
      
    -2.16
    </i>
    -2.08
     Those
    -1.98
     Regardless
    -1.96
     These
    -1.95
         
    -1.92
    POSITIVE LOGITS
    甞
    2.25
    髕
    1.95
     花纹
    1.88
    粜
    1.80
    蔸
    1.80
     pogod
    1.79
     approval
    1.79
    鱨
    1.77
     новом
    1.77
     maravill
    1.76
    Activations Density 0.005%

    No Known Activations