© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106203
    Prev
    Next
    INDEX
    Explanations

    seller

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

    The neuron strongly activates on numeric tokens and measurements (e.g. sizes, quantities, temperatures) in product‐review text.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     весело
    -1.03
     freshly
    -0.96
    werkers
    -0.85
    ACCIÓN
    -0.84
    我们
    -0.82
    romptu
    -0.81
     []:
    -0.81
     الخم
    -0.80
     vekt
    -0.79
     our
    -0.78
    POSITIVE LOGITS
     seller
    1.64
     продав
    1.30
     arrived
    1.20
     sellers
    1.12
    seller
    1.08
    𓏸
    1.05
     vendedor
    1.02
     Seller
    1.00
    Holger
    0.97
     vendeur
    0.93
    Activations Density 0.003%

    No Known Activations