© 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. 68605
    Prev
    Next
    INDEX
    Explanations

    scientific and technical descriptors

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

    This neuron responds to specialized, multi-syllabic technical or scientific terms.

    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
    تحميل
    -1.12
    بسم
    -1.08
    Curios
    -1.08
    ★☆
    -1.08
    Inhalts
    -1.06
    Kommentare
    -1.05
     領
    -1.05
    ★★★★
    -1.05
    Доброго
    -1.04
    Descriere
    -1.02
    POSITIVE LOGITS
        
    1.13
       
    1.10
    mathbb
    1.05
     Perform
    1.03
    unistd
    1.02
    Dub
    0.97
    कर्
    0.97
            
    0.97
    Ủ
    0.95
    <mask>
    0.94
    Activations Density 0.281%

    No Known Activations