© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 50780
    Prev
    Next
    INDEX
    Explanations

    digital content purchases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wavy
    0.47
     znamen
    0.41
     damping
    0.41
     makan
    0.39
     kasa
    0.39
     merak
    0.39
     walkways
    0.38
    ]%
    0.38
     ominous
    0.38
     laminar
    0.38
    POSITIVE LOGITS
     purchases
    0.72
     Purchased
    0.68
    Purch
    0.63
     purchase
    0.63
     Purchases
    0.63
     purchased
    0.61
     compras
    0.59
     Purchase
    0.58
     PURCHASE
    0.58
    Purchase
    0.57
    Activations Density 0.025%

    No Known Activations