© 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. 8005
    Prev
    Next
    INDEX
    Explanations

    quality of life

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

    The neuron fires on occurrences of the word “quality,” especially in “quality of ____” phrases.

    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
     was
    -1.34
    ή
    -1.30
    谂
    -1.29
     Determining
    -1.28
    随后
    -1.28
    odeon
    -1.27
     priorities
    -1.25
     كورة
    -1.23
     Connecting
    -1.22
    
    -1.22
    POSITIVE LOGITS
     of
    1.41
     quality
    1.38
    スポンサーリンク
    1.15
     jūs
    1.14
    oğlu
    1.13
    qualities
    1.12
    quality
    1.12
    Качество
    1.11
     dizaines
    1.11
     qualité
    1.10
    Activations Density 0.070%

    No Known Activations