© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 80617
    Prev
    Next
    INDEX
    Explanations

    Pixel phones & Buds, growth factor, Surface, organized network

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

    technology brand names and scientific terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is triggered by capitalized proper nouns or technical terms—names of products, tools, or specialized biological entities.

    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
     ۶
    -1.43
     pirm
    -1.39
     ۵
    -1.33
    为什么会
    -1.30
    سين
    -1.29
     mettent
    -1.28
     samarbeid
    -1.27
    ⒍
    -1.23
    向けの
    -1.23
     होगा
    -1.23
    POSITIVE LOGITS
     have
    1.79
    );
    
    1.52
    ,”
    1.41
    ];
    
    1.37
    )
    1.32
     if
    1.28
    );
    1.28
     أيضاً
    1.24
     when
    1.23
    lgari
    1.21
    Activations Density 0.175%

    No Known Activations