© 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. 33047
    Prev
    Next
    INDEX
    Explanations

    table name or entity name

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

    This neuron flags code‐style tokens—identifiers, keywords, and other programming‐language constructs—marking code snippets.

    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
    हरु
    -0.83
    movieId
    -0.82
    Fär
    -0.82
     lặng
    -0.81
     Francois
    -0.78
     SMA
    -0.76
    recipes
    -0.76
    fieldId
    -0.75
    owment
    -0.75
     člá
    -0.74
    POSITIVE LOGITS
     table
    1.97
     tables
    1.84
    TableName
    1.58
     tableName
    1.55
     entity
    1.52
    Table
    1.37
     Table
    1.35
    Tables
    1.33
    tableName
    1.32
    table
    1.30
    Activations Density 0.087%

    No Known Activations