© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 170144
    Prev
    Next
    INDEX
    Explanations

    purchase and sales notifications

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

    acquiring or purchasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    境界層
    0.48
     تقول
    0.48
    interval
    0.46
    Boundary
    0.46
    asked
    0.46
    argue
    0.45
    punctuation
    0.45
    젹
    0.43
    concat
    0.43
     Гла
    0.42
    POSITIVE LOGITS
     satın
    0.59
     purchase
    0.58
     purch
    0.54
     zakup
    0.52
     ಖರೀ
    0.50
     PURCHASE
    0.49
     tüket
    0.48
    出荷
    0.47
     pener
    0.46
     penyeleng
    0.45
    Activations Density 0.006%

    No Known Activations