© 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. 10685
    Prev
    Next
    INDEX
    Explanations

    explains the purpose or use

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

    The neuron detects occurrences of the word “used.”

    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
    ᠌
    -2.06
    
    -1.93
    絝
    -1.83
    ᠋
    -1.81
    pecified
    -1.76
    僦
    -1.72
    produces
    -1.70
    ⏑
    -1.68
    罍
    -1.64
    represents
    -1.63
    POSITIVE LOGITS
     of
    1.90
     would
    1.67
     to
    1.65
     if
    1.60
    (
    1.53
    4
    1.52
     new
    1.51
     that
    1.45
     use
    1.44
    /
    1.38
    Activations Density 0.063%

    No Known Activations