© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21136
    Prev
    Next
    INDEX
    Explanations

    fleet

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

    The neuron activates specifically on the word “fleet.”

    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
    ᠌
    -2.70
    黥
    -2.69
    艄
    -2.67
    暝
    -2.56
    缡
    -2.52
    朏
    -2.50
    
    -2.45
    usstsein
    -2.41
    噼
    -2.33
    籮
    -2.33
    POSITIVE LOGITS
    i
    3.14
    」
    2.84
    I
    2.80
    也
    2.70
     '
    2.67
    是非常
    2.61
    中的
    2.59
    ers
    2.58
    '
    2.55
    l
    2.52
    Activations Density 0.002%

    No Known Activations