© 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. 15796
    Prev
    Next
    INDEX
    Explanations

    prices, rates, measurements, and costs

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

    approximate costs and prices

    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
     ermög
    0.50
     vytvá
    0.49
     しかし
    0.48
    <unused47>
    0.47
    PhysicalDevice
    0.46
    eningkatan
    0.46
     wych
    0.46
     ordinairement
    0.45
    ⦕
    0.44
     целью
    0.44
    POSITIVE LOGITS
     quoted
    0.69
     updated
    0.63
     includes
    0.60
     refers
    0.57
     calculated
    0.57
     recalculated
    0.56
     measurements
    0.55
     adjusted
    0.54
     referring
    0.54
     measured
    0.54
    Activations Density 0.059%

    No Known Activations