© 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. 40963
    Prev
    Next
    INDEX
    Explanations

    musical instruments

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

    The neuron primarily detects occurrences of the word “instrument” (and its morphological variants) in the text.

    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
     lakini
    -1.56
    我们的
    -1.52
    it
    -1.48
     basah
    -1.48
    ma
    -1.45
    化妆
    -1.42
     compelled
    -1.38
    an
    -1.35
     entrenched
    -1.35
     celebratory
    -1.34
    POSITIVE LOGITS
    requestCode
    1.67
     einschließlich
    1.66
     are
    1.63
    URLEncoder
    1.60
    ----</
    1.59
    enyum
    1.59
    contentLoaded
    1.52
     المناطق
    1.52
     vand
    1.52
     บาท
    1.49
    Activations Density 0.005%

    No Known Activations