© 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. 10-GEMMASCOPE-RES-131K
    7. 3611
    Prev
    Next
    INDEX
    Explanations

    technical terms and proper nouns

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

    The neuron fires on relatively rare or specialized “content” tokens—proper names, technical terms, or unusual/composite words—rather than common function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     适合
    -2.42
    خوش
    -2.22
     они
    -2.19
    
    -2.19
    讓你
    -2.14
     upsetting
    -2.13
     They
    -2.11
    </b>
    -2.11
     supplementing
    -2.11
    ↵↵
    -2.03
    POSITIVE LOGITS
    al
    3.27
    鼋
    2.69
    c
    2.67
    U
    2.64
    ing
    2.61
    呖
    2.58
    <em>
    2.52
    an
    2.45
    on
    2.45
    趵
    2.36
    Activations Density 0.011%

    No Known Activations