© 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. 103484
    Prev
    Next
    INDEX
    Explanations

    SQL queries and database operations

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

    The neuron fires primarily on numeric literals (e.g. version numbers, error‐codes, ports) in code and technical text.

    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
     moest
    -0.77
    ╤
    -0.77
    خذ
    -0.77
    rums
    -0.76
    いく
    -0.75
    Ports
    -0.73
     tackle
    -0.73
    ابع
    -0.72
    lý
    -0.72
     Robb
    -0.71
    POSITIVE LOGITS
     SQ
    0.85
    pearance
    0.77
    Ǿ
    0.75
     жур
    0.75
     Verwaltung
    0.74
    habits
    0.74
     virtues
    0.73
     Favor
    0.73
    шина
    0.73
    疚
    0.72
    Activations Density 0.018%

    No Known Activations