© 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. 34-GEMMASCOPE-RES-131K
    7. 38145
    Prev
    Next
    INDEX
    Explanations

    combination, combo, special

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

    The neuron activates on menu item names—especially Vietnamese dish names—in restaurant listings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    mtable
    -0.84
    '>{
    -0.81
    rinha
    -0.78
    querque
    -0.77
     toàn
    -0.76
     グラン
    -0.75
    
    -0.75
    赏
    -0.74
    interrupted
    -0.73
    ukunfts
    -0.73
    POSITIVE LOGITS
     Combination
    1.46
     combination
    1.43
     Combo
    1.23
     combo
    1.21
    Combination
    1.20
    Combo
    1.02
    combination
    0.97
     combos
    0.96
     kombinasi
    0.92
     Special
    0.87
    Activations Density 0.008%

    No Known Activations