© 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. 69331
    Prev
    Next
    INDEX
    Explanations

    foreign language greetings and items

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

    The neuron specializes in spotting mentions of food and meal items in a dining or menu context.

    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
     of
    -1.85
    却又
    -1.38
     både
    -1.23
    却不
    -1.13
    Circa
    -1.13
    かつ
    -1.11
    tığı
    -1.09
    Rendez
    -1.05
    来得
    -1.05
     однако
    -1.05
    POSITIVE LOGITS
     frattempo
    1.32
    toCharArray
    1.30
    שלום
    1.30
     papiers
    1.27
    都
    1.27
     mengucapkan
    1.23
     menghubungi
    1.23
    ⠃
    1.22
    สั่ง
    1.22
    urismo
    1.20
    Activations Density 0.005%

    No Known Activations