© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 29319
    Prev
    Next
    INDEX
    Explanations

    pay for what you use

    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_262k_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
     sprzedaży
    0.39
     സമ്
    0.37
     sale
    0.34
    둥
    0.34
     SRP
    0.34
     полностью
    0.34
    ┼
    0.34
    ிற்ப
    0.33
    ,"%
    0.33
    äng
    0.33
    POSITIVE LOGITS
     paying
    2.44
     Paying
    2.30
    paying
    2.19
    Paying
    2.19
     pays
    1.95
     membayar
    1.93
     pay
    1.87
    pays
    1.66
    pay
    1.65
     pagar
    1.65
    Activations Density 0.012%

    No Known Activations