© 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. 129618
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on sequences of capitalized words or acronyms that signal document titles or section headings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    In fact

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    felizmente
    -1.03
    
    -0.96
     ImportError
    -0.96
     PhpStorm
    -0.95
     едва
    -0.91
     Automobil
    -0.91
    便秘
    -0.91
     примерно
    -0.91
    ὁ
    -0.90
     BIRTHDAY
    -0.89
    POSITIVE LOGITS
     بهد
    1.03
    ḗ
    0.98
    wegen
    0.94
     lutar
    0.94
     použití
    0.94
     causes
    0.93
     pomocí
    0.92
    trica
    0.92
    を選択します
    0.91
     χρησιμοποι
    0.90
    Activations Density 0.019%

    No Known Activations