© 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. 68844
    Prev
    Next
    INDEX
    Explanations

    describing something loaded

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

    The neuron specifically fires on occurrences of the word “loaded.”

    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
    th
    -2.63
    o
    -2.50
    vantaged
    -2.39
    u
    -2.38
    鲧
    -2.33
     الأطفال
    -2.25
    到了
    -2.22
    
    -2.20
    and
    -2.19
    k
    -2.16
    POSITIVE LOGITS
    ścić
    2.44
    );
    2.38
    翾
    2.33
    珖
    2.28
    洐
    2.28
    烔
    2.23
    
    2.19
     specifies
    2.19
    镡
    2.16
     setiap
    2.09
    Activations Density 0.004%

    No Known Activations