© 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. 72602
    Prev
    Next
    INDEX
    Explanations

    blouse, blinds, smoothie

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

    The neuron fires on concrete named products in commercial or marketing contexts—e.g. “smoothie,” “blinds,” “blouse.”

    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
     and
    -2.55
    struzione
    -2.33
    chtenstein
    -2.23
    巿
    -2.09
    
    -2.06
    んびり
    -2.06
    ńst
    -2.06
    台中
    -2.05
    deelte
    -2.02
     剤
    -2.02
    POSITIVE LOGITS
     "
    2.81
     adorned
    2.41
    {
    2.23
    だけではなく
    2.17
    だけでなく
    2.17
     largely
    2.17
    *
    2.13
    ?
    2.06
     exemplifies
    2.06
    ли
    2.03
    Activations Density 0.002%

    No Known Activations