© 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. 34-GEMMASCOPE-RES-131K
    7. 106870
    Prev
    Next
    INDEX
    Explanations

    cheap/affordable prices

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

    The neuron detects commercial or promotional business language—words used in sales offers, pricing announcements, and marketing calls-to-action.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    atiles
    -0.88
    🧳
    -0.82
     Pilipinas
    -0.81
    zzled
    -0.79
     簡単
    -0.78
    boar
    -0.77
    Prä
    -0.77
    actéris
    -0.76
    yszer
    -0.76
    mgren
    -0.75
    POSITIVE LOGITS
     price
    7.78
     prices
    7.53
     pricing
    6.03
    price
    5.56
     Prices
    5.28
    Price
    5.09
     Price
    4.97
    prices
    4.94
    Prices
    4.94
    PRICE
    4.50
    Activations Density 0.213%

    No Known Activations