© 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. 12544
    Prev
    Next
    INDEX
    Explanations

    which is

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

    This neuron is a strong detector for the word “is.”

    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
     of
    -2.11
     даже
    -1.65
     bahkan
    -1.59
    ↵↵
    -1.57
     This
    -1.55
     on
    -1.55
     in
    -1.49
     lakini
    -1.48
     campion
    -1.48
     pekerjaan
    -1.47
    POSITIVE LOGITS
    brainly
    1.84
     cír
    1.80
     why
    1.70
    </b>
    1.66
    什么的
    1.64
    尨
    1.62
     something
    1.57
    艄
    1.56
     και
    1.56
     never
    1.55
    Activations Density 0.021%

    No Known Activations