© 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. 84647
    Prev
    Next
    INDEX
    Explanations

    realm, room, database

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

    This neuron detects code‐style syntax—programming language tokens and punctuation, such as import/package declarations and other code elements.

    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
     Ghosh
    -0.79
     Concepción
    -0.75
     mercury
    -0.75
     Duval
    -0.73
    Meli
    -0.73
     cabling
    -0.72
     Raub
    -0.71
    hes
    -0.71
     campesinos
    -0.71
    AVIS
    -0.69
    POSITIVE LOGITS
     SQLite
    1.30
     database
    1.24
    Cursor
    1.20
    WritableDatabase
    1.17
    数据库
    1.13
     sqlite
    1.11
     Sq
    1.05
    Dao
    1.04
    ContentValues
    1.04
     db
    1.02
    Activations Density 0.032%

    No Known Activations