© 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. 42861
    Prev
    Next
    INDEX
    Explanations

    minors, underage

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

    The neuron fires on occurrences of the word “minor” (and its plural “minors”).

    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
    
    -1.76
     ſome
    -1.53
    quelles
    -1.52
     suivent
    -1.51
    </h4>
    -1.50
    热闹
    -1.50
    дить
    -1.48
    遇到了
    -1.48
     pensent
    -1.46
     DÉ
    -1.45
    POSITIVE LOGITS
    ～！
    1.84
     nawet
    1.72
    नलोड
    1.69
    ïlande
    1.66
     hierbei
    1.61
     erlä
    1.57
    weakSelf
    1.57
     długość
    1.55
    一刻
    1.55
     его
    1.54
    Activations Density 0.014%

    No Known Activations