© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14063
    Prev
    Next
    INDEX
    Explanations

    journal abbreviations or precursors

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

    The neuron fires on sequences of numbers (years, volume and page numbers, and other numeric identifiers) in academic-style references.

    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
     if
    -1.12
    进行
    -0.98
    如果
    -0.98
    と同じ
    -0.95
    Jim
    -0.95
    一般
    -0.93
    Any
    -0.92
    ```
    -0.90
     ブーツ
    -0.90
    的时候
    -0.87
    POSITIVE LOGITS
    Sursa
    1.22
    涿
    1.02
     peup
    0.98
    mortem
    0.94
    ствен
    0.93
    Categorie
    0.93
    
    0.93
    amentals
    0.93
    喏
    0.93
     pê
    0.93
    Activations Density 0.003%

    No Known Activations