© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12858
    Prev
    Next
    INDEX
    Explanations

    throughout

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find occurrences of the word “throughout.”

    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
     With
    -2.58
    <
    -2.28
     for
    -2.27
     if
    -2.25
    e
    -2.20
    )
    -2.13
     G
    -2.11
     from
    -2.09
     C
    -2.08
    <i>
    -2.05
    POSITIVE LOGITS
    妧
    2.94
    蚰
    2.94
    
    2.91
    繙
    2.89
    艄
    2.83
    鱨
    2.75
    
    2.72
    ︕
    2.61
    읭
    2.61
     acheter
    2.59
    Activations Density 0.007%

    No Known Activations