© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9321
    Prev
    Next
    INDEX
    Explanations

    shopping and malls

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

    The neuron strongly activates on mentions of shopping or retail venues (e.g. “shopping,” “shops,” “restaurants”).

    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
     Hinblick
    -1.38
    ).
    -1.34
     {}));
    -1.32
    га
    -1.31
    []>(
    -1.30
    </sup>
    -1.30
    鵟
    -1.25
    ){
    -1.24
    }{
    -1.23
    )}$
    -1.23
    POSITIVE LOGITS
    FINALLY
    1.39
     tornillos
    1.37
    ינ
    1.34
     tratamientos
    1.30
     accesorios
    1.30
     calefacción
    1.29
     grupper
    1.27
     bietet
    1.27
     malls
    1.25
    INSTAGRAM
    1.25
    Activations Density 0.023%

    No Known Activations