© 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. 22-GEMMASCOPE-RES-131K
    7. 93337
    Prev
    Next
    INDEX
    Explanations

    structured data delimiters

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

    The neuron strongly responds to occurrences of “name” (e.g. column identifiers like “First Name,” “Last Name,” or “name”) in SQL or schema contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ّم
    -1.02
    lahraga
    -0.93
    الت
    -0.91
    él
    -0.90
     även
    -0.89
    Μ
    -0.89
    êter
    -0.88
    bę
    -0.88
    getExtras
    -0.88
    蚩
    -0.86
    POSITIVE LOGITS
     their
    1.05
     where
    0.97
     then
    0.92
    𝜇
    0.86
    インナー
    0.86
     jeżeli
    0.85
     number
    0.85
    PLIED
    0.81
    伝統
    0.81
    ueve
    0.80
    Activations Density 0.032%

    No Known Activations